Content uploaded by Simone Bianco
Author content
All content in this area was uploaded by Simone Bianco on Jun 13, 2018
Content may be subject to copyright.
A preview of the PDF is not available
Deep Learning for Logo Recognition
Abstract and Figures
In this paper we propose a method for logo recognition using deep learning. Our recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network (CNN) specifically trained for logo classification, even if they are not precisely localized. Experiments are carried out on the FlickrLogos-32 database, and we evaluate the effect on recognition performance of synthetic versus real data augmentation, and image pre-processing. Moreover, we systematically investigate the benefits of different training choices such as class-balancing, sample-weighting and explicit modeling the background class (i.e. no-logo regions). Experimental results confirm the feasibility of the proposed method, that outperforms the methods in the state of the art.
Figures - uploaded by Simone Bianco
Author content
All figure content in this area was uploaded by Simone Bianco
Content may be subject to copyright.
... The experimental results achieved a top recognition F1-score of 0.909 with a base learning rate of 0.001 at 30000 iterations and with a threshold of 0.4. A method had been proposed in [20] TELKOMNIKA Telecommun Comput El Control Official logo recognition based on multilayer convolutional neural network model (Zahraa Najm Abdullah) 1085 for logo recognition using deep learning. Logo recognition is essential in numerous application domains [21]. ...
Deep learning has gained high popularity in the field of image processing and computer vision applications due to its unique feature extraction property. For this characteristic, deep learning networks used to solve different issues in computer vision applications. In this paper the issue has been raised is classification of logo of formal directors in Iraqi government. The paper proposes a multi-layer convolutional neural network (CNN) to classify and recognize these official logos by train the CNN model on several logos. The experimental show the effectiveness of the proposed method to recognize the logo with high accuracy rate about 99.16%. The proposed multi-layers CNN model proves the effectiveness to classify different logos with various conditions.
In this paper, we study the problem of identifying logos of business brands in natural scenes in an open-set one-shot setting. This problem setup is significantly more challenging than traditionally-studied 'closed-set' and 'large-scale training samples per category' logo recognition settings. We propose a novel multi-view textual-visual encoding framework that encodes text appearing in the logos as well as the graphical design of the logos to learn robust contrastive representations. These representations are jointly learned for multiple views of logos over a batch and thereby they generalize well to unseen logos. We evaluate our proposed framework for cropped logo verification, cropped logo identification, and end-to-end logo identification in natural scene tasks; and compare it against state-of-the-art methods. Further, the literature lacks a 'very-large-scale' collection of reference logo images that can facilitate the study of one-hundred thousand-scale logo identification. To fill this gap in the literature, we introduce Wikidata Reference Logo Dataset (WiRLD), containing logos for 100K business brands harvested from Wikidata. Our proposed framework that achieves an area under the ROC curve of 91.3% on the QMUL-OpenLogo dataset for the verification task, outperforms state-of-the-art methods by 9.1% and 2.6% on the one-shot logo identification task on the Toplogos-10 and the FlickrLogos32 datasets, respectively. Further, we show that our method is more stable compared to other baselines even when the number of candidate logos is on a 100K scale.
Addressing issues related to multi-label classification is relevant in many fields of applications. In this work. We present a multi-label classification architecture based on Multi-Branch Neural Network Model (MBNN) that permits the network to encode data from multiple semi-parallel subnetworks or layers outputs separately. Different types of neural networks can be used in the MBNN, but the proposal is made with Convolutional Neural Networks subnetworks, trained, and joined in classifying the outputs (i.e., labels). The proposed work makes it possible to perform incremental changes on existing Multitask Learning architectures for an adaptation to the multi-label classification. These transformations lead us to define two new architectures (neural network multi-outputs and neural network multi-features) using the feature extractors from the pre-trained neural networks. The empirical and statistical results verify that the proposed multibranch neural network architecture performs better than other simple multi-label classification architectures. Later, the “network with multi-features” obtained the highest classification score than other deep neural networks with 83.31% of the f1-score for the Amazon rainforest dataset. The f1-score values are 88.81% for Pascal VOC 2007 dataset, 87.71% for Nuswide, and 88.64% for Pascal VOC 2012.
When logos are increasingly created, logo detection has gradually become a research hotspot across many domains and tasks. Recent advances in this area are dominated by deep learning-based solutions, where many datasets, learning strategies, network architectures, etc. have been employed. This paper reviews the advance in applying deep learning techniques to logo detection. Firstly, we discuss a comprehensive account of public datasets designed to facilitate performance evaluation of logo detection algorithms, which tend to be more diverse, more challenging, and more reflective of real life. Next, we perform an in-depth analysis of the existing logo detection strategies and the strengths and weaknesses of each learning strategy. Subsequently, we summarize the applications of logo detection in various fields, from intelligent transportation and brand monitoring to copyright and trademark compliance. Finally, we analyze the potential challenges and present the future directions for the development of logo detection to complete this survey.
In this paper a method of recognizing logos of the brand of cosmetic products using deep learning. There are several of hoax product which easily copies the famous brand’s logo and deteriorates the company’s image. The machine learning has proved to be useful in various of the fields like medical, object detection, vehicle logo recognitions. But till now very few of the works have been performed in cosmetic field. This field is covered using the model sequential convolutional neural network using Tensorflow and Keras. For the visual representation of the result Tensorboard is used. Work have been started with two of the brands-Lakme and L’Oreal. Depending upon the success of this technique, further brands for logo may be added for recognition. The accuracy of approximately 80% was obtained using this technique.
We propose a method for localization and classification of brand logos in natural images. The system has to overcome multiple challenges such as perspective deformations, warping, variations of the shape and colors, occlusions, background variations. To deal with perspective variation, we rely on homography matching between the SIFT keypoints of logo instances of the same class. To address the changes in color, we construct a weighted graph of logo interconnections that is further analyzed to extract potentially multiple instances of the class. The main instance is built by grouping the keypoints of the graph connected logos onto the central image. The secondary instance is needed for color inverted logos and is obtained by inverting the orientation of the main instance. The constructed logo recognition system is tested on two databases (FlickrLogos-32 and BelgaLogos), outperforming state of the art with more than 10 % accuracy.
Recently, there has been a flurry of industrial activity around logo
recognition, such as Ditto's service for marketers to track their brands in
user-generated images, and LogoGrab's mobile app platform for logo recognition.
However, relatively little academic or open-source logo recognition progress
has been made in the last four years. Meanwhile, deep convolutional neural
networks (DCNNs) have revolutionized a broad range of object recognition
applications. In this work, we apply DCNNs to logo recognition. We propose
several DCNN architectures, with which we surpass published state-of-art
accuracy on a popular logo recognition dataset.
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R-CNN [5] have reduced the running time of these detection networks, exposing region pro-posal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolu-tional features. For the very deep VGG-16 model [18], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2% mAP) and 2012 (70.4% mAP) using 300 proposals per image. The code will be released.
Objective methods for assessing perceptual image quality have traditionally attempted to quantify the visibility of errors between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a Structural Similarity Index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. A MatLab implementation of the proposed algorithm is available online at http://www.cns.nyu.edu/~lcv/ssim/.
In this paper we explore the benefits of synthetically generated data for the task of company logo detection with deep-learned features in the absence of a large training set. We use pre-trained deep convolutional neural networks for feature extraction and use a set of support vector machines for classifying those features. In order to generate sufficient training examples we synthesize artificial training images. Using a bootstrapping process, we iteratively add new synthesized examples from an unlabeled dataset to the training set. Using this setup we are able to obtain a performance which is close to the performance of the full training set.
Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets. © 2014 Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov.
In this paper we propose a method for logo recognition based on Convolutional Neural Networks, instead of the commonly used keypoint-based approaches. The method involves the selection of candidate subwindows using an unsupervised segmentation algorithm, and the SVM-based classification of such candidate regions using features computed by a CNN. For training the neural network we augment the training set with artificial transformations, while for classification we exploit a query expansion strategy to increase the recall rate. Experiments were performed on a publicly-available dataset that was also corrupted in order to investigate the robustness of the proposed method with respect to blur, noise and lossy compression.