No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Digital Video Processing Techniques and Applications
Abstract
Fundamentals of Motion Estimation and Motion CompensationGeneral Methodologies in Motion EstimationMotion Estimation AlgorithmsVideo Enhancement and Noise ReductionCase Study: Object Segmentation and Tracking in the Presence of Complex Background
Tutorial 22.1: Block-based Motion EstimationTutorial 22.2: Intraframe and Interframe Filtering TechniquesProblems
... Videos, the modern shape of the old theatre, have evolved, and we can see many new technologies. One such application is a hologram which is not common and so expansive that it cannot be used at the consumer level (Marques 2011). However, 3D visual systems are now commonly used in the consumer market. ...
Digital videos have numerous applications, ranging from amateur videos on social media to complex imaging of space objects. Most of the time, different images and videos are combined to get a large field of view, including a simple panoramic image or detailed images of Mars created by stitching over 900 images. In most cases, different images are stitched linearly on a plane. However, recently researchers have stitched images and videos together to produce 360-degree views. In these 360-degree videos, there is primarily the main camera or a set of cameras that covers the scene. In contrast, another concept—the 3D view—captures depth along with the height and width of the images. The proposed work focuses on developing a composite visual space that captures a scene with different cameras and combines it accordingly. One of the essential features of the proposed work is image normalization. Images acquired from multiple sources are of various sizes, orientations, and brightness levels. A set of eight augmented normalized images are formed in a circular form where each image has its positional features. The article focuses on the normalization process of the images captured from different cameras with different specifications so that they can be used to form the proposed visual space. The results of the proposed algorithm are compared for time and space. The proposed algorithm uses 45–70% less computation. On average, this method normalizes with only 52% of computations for the selected dataset. This proposed algorithm us less computational and storage resource. In term if computational, it is faster as most of the calculations involve shifts in the integer values and the range of the values are from 0 to 255 that can fit in 8-bit integer. Most of the other methods uses complex real number equations that are computationally expansive and use more bits per pixels. Moreover, this approach requires a smaller number of shifts because of which quality is affected almost insignificantly.
Nowadays, there exist many video datasets that consume more in size. Searching for a certain pattern in the video dataset became very difficult. Hence, the proposed system takes certain patterns and searches the videos that consist of such patterns. This system requires converting the appropriate video into the text and saves such files as a respective video file name with suffix text as a keyword. Such a conversion should be done efficiently and manage the files in the cloud. Searching multiple patterns in the set of videos and displaying which videos consist of which patterns. These statistics are much useful for further analysis. Such analysis is helpful in justifying which videos are useful for their concern field. The advantages obtained are searching in an unknown environment such as a video dataset, producing the videos only for the given patterns, and methodology is made is simple and efficient. Not only destination type is video, but it could be even other types also. In such a situation also, the pattern will be processed in that environment and generates a report. Here, efficient text mining occurs on any video dataset. In the future, the input could be taken as audio-only and searching that given audio bit in the given audio file.
Data mining is capable of giving and providing the hidden, unknown,
and interesting information in terms of knowledge in healthcare industry. It is useful
to form decision support systems for the disease prediction and valid diagnosis of
health issues. The concepts of data mining can be used to recommend the solutions
and suggestions in medical sector for precautionary measures to control the disease
origin at early stage. Today, diabetes is a most common and life taking syndrome
found all over theworld. The presence of diabetes itself is a cause tomany other health
issues in the form of side effects in human body. In such cases when considered, a
need is to find the hidden data patterns from diabetic data to discover the knowledge so
as to reduce the invisible health problems that arise in diabetic patients. Many studies
have shown that AssociativeClassification concept of dataminingworks well and can
derive good outcomes in terms of prediction accuracy. This research work holds the
experimental results of the work carried out to predict and detect the by-diseases in
diabetic patients with the application of Associative Classification, and it discusses
an improved algorithmic method of Associative Classification named Associative
Classification using Maximum Threshold and Super Subsets (ACMTSS) to achieve
accuracy in better terms.
Keywords Knowledge · By-disease · Maximum threshold · Super subsets ·
ACMTSS · Associative Classification
ResearchGate has not been able to resolve any references for this publication.