Article

A Study on the Effectiveness of Digital Signage Advertisement

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

With the advancement of network and multimedia technologies, many computer convergence applications have emerged. Digital signage via the Internet is one of the innovative uses adopted by the commercial industry. Commercials are a part of our daily lives, for instance, indoor and outdoor digital signs can be found in department stores and baseball parks, respectively. For a new media or commercial advertisement channel, it is important to measure and monitor its effectiveness. Here, we use data mining to investigate the results of digital advertising in broadcasting through the digital signage system. In this study, we aimed to understand the effectiveness of digital signage - whether its advertisement attracts the target customers. Based on the commercial programs requested by clients, we used face recognition and data mining technologies to recognize the facial features of customers from different angles when facing the display screen. Then we determined whether a consumer is watching advertisements and tracked the viewing duration. Lastly we analyzed the obtained data to evaluate the effectiveness of the digital signage advertisement. Our experiments show that our approach is feasible and can meet users¡¦ expectations.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... It displays menus with high visibility to simplify ordering food in fast food restaurants, cafes, and movie theaters. In addition, digital signage is actively used as advertising signage [1]- [3]. For example, a huge digital signage is being used as an advertising sign in Times Square, Broadway, New York, USA, demonstrating the effect of digital signage on attracting visitors by converting media art beyond the purpose of promoting advertisements. ...
... For interpolation we used Lagrange equation as (1). As we designed an order of polynomial to 1, interpolation equation f becomes linear function l i since cardinal function is composed of l 0 = x − x 1 x 0 − x 1 ...
Full-text available
Article
This study proposes a framework for an intelligent agent information service using digital human and deep learning technology. The framework can recognize the identity of individuals using facial features and provide personalized services through a digital human. The personalized service is defined by a relevance graph based on personal data collected in advance. The proposed system can continuously evolve to recommend customized services using relevance graphs and dynamic data processing, gradually become more intelligent using additionally collected data. Moreover, it uses animation keyframe interpolation for natural and seamless digital human interaction and provides visual effects that are synchronized based on specific information collected for the intuitive service. The proposed system was tested on a school domain for two months, and a statistical domain feedback system based on a mathematical model that predicts service usage per unit time was developed using the recorded information. Additionally, we evaluate our system through user experience surveys.
... Many types of research about vision-based DOOH systems have been studied and implemented to collect the audience measurement with digital cameras [1,7,8,9]. The audience measurement metric includes the number of audiences, time duration, distance, and height. ...
Full-text available
Article
Digital signage is widely utilized in digital-out-of-home (DOOH) advertising for marketing and business. Recently, the combination of the digital camera and digital signage enables the advertiser to gather the audience demographic for audience measurement. Audience measurement is useful for the advertiser to understand the audience's behavior and improve their business strategies. When an audience is facing the digital display, the vision-based DOOH system will process the audience's face and broadcast a personalized advertisement. Most of the digital signage is available in an uncontrolled environment of public areas. Thus, it poses two main challenges for the vision-based DOOH system to track the audience's movement, which are multiple adjacent faces and occlusion by passer-by. In this paper, a new framework is proposed to combine the digital signage with a depth camera for tracking multi-face in the three-dimensional (3D) environment. The proposed framework extracts the audience's face centroid position (x, y) and depth information (z) and plots into the aerial map to simulate the audience's movement that is corresponding to the real-world environment. The advertiser can further measure the advertising effectiveness through the audience's behavior.
... For instance, Taiwan news attracted a larger number of viewers when compared to International news, but the viewers stayed for a shorter period of time. Differently from [3], in the research of [8], demographic viewers analysis (eg, gender and age considerations) was not performed. ...
Conference Paper
In this paper, we propose an approach to study and to model audience attention to videos within digital signage scenarios. An experimental setup was conceived to simultaneously display videos of various categories and to capture videos from the audience and surrounding environment. Face analysis via a deep neural network is performed to estimate gender and age groups. In the proposed approach, a Bayesian Network is built to model possible relationships between the audience's age, gender and face size (which is indicative of the distance to the display) and the video content types. A publicly available video dataset of 152 videos was created for displaying purposes. An experimental evaluation indicated varying degrees of attention to different videos, depending on age and gender. The area under the ROC curve of the built Bayesian Network was 0.82. The proposed approach allows to better understand the possible relationships between audience demographics and video contents, which may, in turn, be useful for displaying the most appropriate content to a particular audience, help with the automatic insertion of ads (based on audience categories), among other applications.
... Digital signage at a fixed location is integrated with a big TV and networked computer to deliver the information to the audience. Moreover, a study shows that today's digital signage has different types of media elements that can be used to present the content via online updates and real-time program scheduling [9]. As such, digital signage has become a viable advertising option for advertisers in today's world that relies heavily on online advertising because of its various benefits [10]. ...
Full-text available
Article
This study proposes a measurable scale to gauge advertising effectiveness of digital signage. Gender study was performed on the constructs to supplement the findings. "Engagement" and "Involvement", two well-known constructs were used to find out the advertising effectiveness using digital signage. A real-time experiment was conducted and the survey data (N = 221) were analyzed, presenting descriptive analysis and T-test analysis across all items among the constructs. The findings reveal that both "Engagement" and "Involvement" are significant contributors to advertising effectiveness in the context of digital signage. Findings also suggest that females tend to enjoy the advertisements more with a higher degree of advertisement related experiences.
... Main usage purposes of digital signage are corporate communications, corporate messaging, corporate announcements, advertising and promoting products, entertainment, public information systems such as news, headlines, weather, and menu information such as digital menu boards with information on pricing, ingredients and nutritional facts. Effectiveness of Digital Signage Advertisements is one of the most important research topic of information engineering [3]. ...
Article
This paper is about a remotely managed digital signage system design considering embedded system design rules and characteristics. Digital signage system design is based on various methods of using computer and television screens as well as other kinds of display devices in ways that are as efficient as possible to provide advertising and information to people in public areas. In modern digital signage systems, the screens are divided into regions and layers, and the content on the screens is made up of several files. The goals of this study are broadcasting information, advertisements at display contents in public areas such as; subways, buses, malls, city squares and control these digital signs remotely.
Article
Digital signage in public spaces is generally silent. However, the emission of sound with the aim of generating recallability produces noise, which can be uncomfortable for passersby in the surrounding space, resulting in a loss of acoustic comfort. In this paper, we implement an On-Demand pinpoint audio system in which sound is delivered only to one person, and only the sound of the advertisement that attracts the person’s attention is played. By applying this system to passersby, this paper examines the system’s influence on advertisement recallability and acoustic comfort. Additionally, we detect the categories of advertisements affecting the advertisement recallability and acoustic comfort when digital signs emit sound. Through experiments with 30 participants, acoustic comfort is maintained and On-Demand System can reduce noise level compared to loudspeaker. In addition, we collected participants’ self-reported recallabilities and analyzed by advertising category. These results show that music-dominating advertisements presented by the On-Demand System were more recallable than silent and other advertisement categories. These results indicate the possibility of personalization of the advertising information and the perceptual spaces, even if the individuals are in public spaces.
Full-text available
Conference Paper
Currently, there are environments in which public devices are positioned at strategic points such as elevators, hallways and showcases. Although these devices are visible to a lot of consumers, advertisers have little information about users who are present in the environment. However, such information may be acquired from the users’ personal devices in a Pervasive Environment, where computing devices are seamlessly integrated to the users’ life. In this way, Pervasive Advertising may be applied to maximize the relevance of the advertised products by adapting to the group of people in the environment. In this work, we present a Coloured Petri Net model to verify how the symbiotic use of the devices may be applied for creating a group-context, and how Pervasive Advertising impacts on the relevance of displayed advertisements.
Full-text available
Conference Paper
Detecting anomalous traffic is a crucial part of managing IP networks. In recent years, network-wide anomaly de- tection based on Principal Component Analysis (PCA) has emerged as a powerful method for detecting a wide vari- ety of anomalies. We show that tuning PCA to operate effectively in practice is difficult and requires more robust techniques than have been presented thus far. We analyze a week of network-wide traffic measurements from two IP backbones (Abilene and Geant) across three different traffic aggregations (ingress routers, OD flows, and input links), and conduct a detailed inspection of the feature time se- ries for each suspected anomaly. Our study identifies and evaluates four main challenges of using PCA to detect traf- fic anomalies: (i) the false positive rate is very sensitive to small differences in the number of principal components in the normal subspace, (ii) the effectiveness of PCA is sensi- tive to the level of aggregation of the traffic measurements, (iii) a large anomaly may inadvertently pollute the normal subspace, (iv) correctly identifying which flow triggered the anomaly detector is an inherently challenging problem.
Full-text available
Conference Paper
We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates.
Full-text available
Conference Paper
This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.
Full-text available
Article
Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors)
Full-text available
Article
Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face, regardless of its 3D position, orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research
Article
This paper describes a visual object detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the "Integral Image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features and yields extremely efficient number of critical visual features and yields extremely efficient classifiers [6]. The third contribution is a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. A set of experiments in the domain of face detection are presented. The system yields face detection performace comparable to the best previous systems [18, 13, 16, 12, 1]. Implemented on a conventional desktop, face detection proceeds at 15 frames per second.
Article
Efficiency issue in automatic web-based information retrieval research becomes an important issue to users. Most knowledge and materials on the Internet is in either semi-structured or unstructured hypermedia form. When users found a webpage as searching result from the Internet for self-learning, sometimes they may not understand the meanings of specific part of the retrieved webpage easily. They need to spend a lot of time in finding more references manually to make they get clear idea of the original retrieved webpage told. If an agent can be developed to reconstruct the webpage that the users are browsing by inserting additional self-explainable documents' links at appropriate places in the original webpage, it will be perfect. This research uses formal concept analysis (FCA) and association rule methodology (ARM) to develop a Keyword Association Lattice (KAL). With the KAL, the webpages accessed by users can be analyzed and reconstructed automatically. A pedagogical software agent called K-Navi for users doing survey and self-learning on the Internet is developed.
Article
Viola and Jones [9] introduced a method to accurately and rapidly detect faces within an image. This technique can be adapted to accurately detect facial features. However, the area of the image being analyzed for a facial feature needs to be regionalized to the location with the highest probability of containing the feature. By regionalizing the detection area, false positives are eliminated and the speed of detection is increased due to the reduction of the area examined.
Article
We present a methodology for sequence classification, which employs sequential pattern mining and optimization, in a two-stage process. In the first stage, a sequence classification model is defined, based on a set of sequential patterns and two sets of weights are introduced, one for the patterns and one for classes. In the second stage, an optimization technique is employed to estimate the weight values and achieve optimal classification accuracy. Extensive evaluation of the methodology is carried out, by varying the number of sequences, the number of patterns and the number of classes and it is compared with similar sequence classification approaches.
Article
In this paper, we propose a novel face detection method based on the MAFIA algorithm. Our proposed method consists of two phases, namely, training and detection. In the training phase, we first apply Sobel's edge detection operator, morphological operator, and thresholding to each training image, and transform it into an edge image. Next, we use the MAFIA algorithm to mine the maximal frequent patterns from those edge images and obtain the positive feature pattern. Similarly, we can obtain the negative feature pattern from the complements of edge images. Based on the feature patterns mined, we construct a face detector to prune non-face candidates. In the detection phase, we apply a sliding window to the testing image in different scales. For each sliding window, if the slide window passes the face detector, it is considered as a human face. The proposed method can automatically find the feature patterns that capture most of facial features. By using the feature patterns to construct a face detector, the proposed method is robust to races, illumination, and facial expressions. The experimental results show that the proposed method has outstanding performance in the MIT-CMU dataset and comparable performance in the BioID dataset in terms of false positive and detection rate.
Conference Paper
Recently Viola et al. have introduced a rapid object detection scheme based on a boosted cascade of simple feature classifiers. In this paper we introduce and empirically analysis two extensions to their approach: Firstly, a novel set of rotated haar-like features is introduced. These novel features significantly enrich the simple features of (6) and can also be calculated efficiently. With these new rotated features our sample face detector shows off on average a 10% lower false alarm rate at a given hit rate. Secondly, we present a through analysis of different boosting algorithms (namely Discrete, Real and Gentle Adaboost) and weak classifiers on the detection performance and computational complexity. We will see that Gentle Adaboost with small CART trees as base classifiers outperform Discrete Adaboost and stumps. The complete object detection training and detection system as well as a trained face detector are available in the Open Computer Vision Library at sourceforge.net (8).
Article
In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone-Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in ℝn. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.
Conference Paper
In this work we present a new method based on PSO (particle swarm optimization) to optimize templates for frontal face detection. In the past, several methods for face detection have been developed using face templates. These templates are based on common face features such as eyebrows, nose and mouth. Templates have been applied to a directional image containing faces computing a line integral to detect faces with high accuracy. In this paper, the PSO is used to select new templates optimizing its size and response to a face in the directional image. The method was tested on a database composed of two video sequences and compared to the results of the traditional anthropometric templates that contain features from the eyebrow, nose and mouth. Results show that templates selected by PSO have significant better performance in the estimation of face size and the line integral value. In both sequences face detection reached 99% and 100%. The templates have fewer number of points compared to the traditional anthropometric templates which will lead to lower processing time.
Article
Sampling has been recognized as an important technique to improve the efficiency of clustering. However, with sampling applied, those points which are not sampled will not have their labels after the normal process. Although there is a straightforward approach in the numerical domain, the problem of how to allocate those unlabeled data points into proper clusters remains as a challenging issue in the categorical domain. In this paper, a mechanism named MAximal Resemblance Data Labeling (abbreviated as MARDL) is proposed to allocate each unlabeled data point into the corresponding appropriate cluster based on the novel categorical clustering representative, namely, N-Nodeset Importance Representative(abbreviated as NNIR), which represents clusters by the importance of the combinations of attribute values. MARDL has two advantages: (1) MARDL exhibits high execution efficiency; (2) MARDL can achieve high intra-cluster similarity and low inter-cluster similarity, which are regarded as the most important properties of clusters, thus benefiting the analysis of cluster behaviors. MARDL is empirically validated on real and synthetic data sets, and is shown to be not only more efficient than prior methods but also attaining results of better quality.
A Study on Consumer Attitudes toward Outdoor Advertising - Using Digital Signage as An Example. Electronic Theses and Dissertations System
  • Jia-Yong Dong
Neural Network-Based Face Detection
  • H A Rowley
  • S Baluja
  • T Kanade
H. A. Rowley, S. Baluja, T. Kanade, "Neural Network-Based Face Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, pp. 23-38, 1998.
Enhancing Digital Advertising Using Dynamically Configurable Multimedia
  • J V Harrison
  • A Andrusiewicz
J. V. Harrison and A. Andrusiewicz, Enhancing Digital Advertising Using Dynamically Configurable Multimedia, 2003 IEEE International Conference on Multimedia and Expo, Las Vegas, NV, 2003, pp. 717-720.
A Study on Consumer Attitudes toward Outdoor Advertising --Using Digital Signage as an Example
  • J.-Y. Dong
J.-Y. Dong, A Study on Consumer Attitudes toward Outdoor Advertising --Using Digital Signage as an Example, Master Thesis, National Dong Hwa University, Hualien, Taiwan, 2007.
Face Recognition using Principal Component Analysis and RBF Neural Networks
  • S Thakur
  • J K Sing
  • D K Basu
  • M Nasipuri
  • M Kundu
S. Thakur, J. K. Sing, D. K. Basu, M. Nasipuri and M. Kundu, Face Recognition using Principal Component Analysis and RBF Neural Networks, International Journal of Simulation Systems, Science & Technology, Vol. 10, No. 5, pp. 7-15, September, 2009.
  • J Shlens
J. Shlens, A Tutorial on Principal Component Analysis, 2005, http://www.cs.cmu.edu/~elaw/papers/ pca.pdf
Face Detection Using Haar Cascades
  • Opencv
OpenCV, Face Detection Using Haar Cascades, 2012, http://docs.opencv.org/master/d7/d8b/tutorial_ py_face_detection.html#gsc.tab=0