Wyniki wyszukiwania - BazTech

1

Overview of Object Detection and Tracking based on Block Matching Techniques

Samdurkar Apurva S., Kamble Shailesh D., Thakur Nileshsingh V., Patharkar Akshay S.

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

313--319

EN

Object tracking is one of the vital fields of computer vision that detects the moving object from a video sequence. Object detection is used to detect the object present in the video and to find the exact location of that object. The object tracking can be applied in various fields that include video surveillance, robot vision, traffic monitoring, automated civil or military surveillance system, traffic monitoring, human-computer interaction, vehicle navigation, biomedical image analysis, medical imaging and much more. The object tracking algorithm requires tracking the object in each frame of the video. A common approach is to use the background subtraction, which eliminates the common static background, resulting into foreground region showing the presence of the desired object. Block matching technique is the most popular technique for computing the motion vectors between the two frames of video sequences and different searching techniques are available to compute motion vectors between frames. Still, there is a scope for improvement in modifying or developing a new shape pattern for block matching motion estimation to find out and track the object in the video. This paper presents the several object detection and tracking methods and how block matching can be used to track object from a video.

2

Metadata based Text Mining for Generation of Side Information

Bhanuse Shraddha S., Kamble Shailesh D., Thakur Nileshsingh V., Patharkar Akshay S.

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

135--141

EN

Text mining is knowledge analyzing technique to find a pattern. The side information is also called as metadata in most of the metadata based text mining applications. The side information consisting of large data in terms of weblogs, metadata, and non-textual data i.e. image/video, etc. This large data present in the unprocessed form which cannot be used for further text mining. Therefore, metadata based text mining algorithms are used to mine the useful information. In this paper, the proposed approach uses the different kind of pre-processing steps i.e. splitting, tokenize, steaming, parsing and chunking. For generating the side information i.e. title, name, affiliation, email address, place etc. a natural language processing (NLP) is used. To achieve the effective clustering, the proposed approach uses a classical partitioning method with a probabilistic model. The proposed approach is compared in terms of time required for mining of words, accuracy, and efficiency. The presented result shows that, the proposed approach performs better in terms of accuracy and running time. In future, a Security is provided for metadata based side information generation using Intrusion Detection System (IDS).

3

Evaluation of Apriori Algorithm on Retail Market Transactional Database to get Frequent Itemsets

Gaikwad Pooja R., Shailesh D. Kamble Shailesh D., Thakur Nileshsingh V., Patharkar Akshay S.

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

187--192

EN

In Data mining the concept of association rule mining (ARM) is used to identify the frequent itemsets from large datasets. It defines frequent pattern mining from larger datasets using Apriori algorithm \& FP-growth algorithm. The Apriori algorithm is a classic traditional algorithm for the mining all frequent itemsets and association rules. But, the traditional Apriori algorithm have some limitations i.e. there are more candidate sets generation \& huge memory consumption, etc. Still, there is a scope for improvement to modify the existing Apriori algorithm for identifying frequent itemsets with a focus on reducing the computational time and memory space. This paper presents the analysis of existing Apriori algorithms and results of the traditional Apriori algorithm. Experimentation carried out on transactional database i.e. retail market for getting frequent itemsets. The traditional Apriori algorithm is evaluated in terms of support and confidence of transactional itemsets.

4

An Overview of Block Matching Algorithms for Motion Vector Estimation

Khawase Sonam T., Kamble Shailesh D, Thakur Nileshsingh V., Patharkar Akshay S.

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

217--222

EN

In video compression technique, motion estimation is one of the key components because of its high computation complexity involves in finding the motion vectors (MV) between the frames. The purpose of motion estimation is to reduce the storage space, bandwidth and transmission cost for transmission of video in many multimedia service applications by reducing the temporal redundancies while maintaining a good quality of the video. There are many motion estimation algorithms, but there is a trade-off between algorithms accuracy and speed. Among all of these, block-based motion estimation algorithms are most robust and versatile. In motion estimation, a variety of fast block based matching algorithms has been proposed to address the issues such as reducing the number of search/checkpoints, computational cost, and complexities etc. Due to its simplicity, the block-based technique is most popular. Motion estimation is only known for video coding process but for solving real life applications many researchers from the different domain are attracted towards block matching algorithms for motion vector estimation.This paper is a review of various block matching algorithms based on shapes and patterns as well as block matching criteria used for motion estimation.