Image Pre-processing Using Angular 7

- Background
- Introduction
- Literature Survey
- Algorithms / Approach
- System Design
- Comparison
- Dashboards - Visualization
- Applications
- Conclusion and Future Scope
- References

Transcript

1. Image Pre-processing using Angular 7 Kunal Sharma When you Visualize, then you Materialize.
2. Outline • Background • Introduction • Literature Survey • Algorithms / Approach • System Design • Comparsion • Dashboards - Visualization • Applications • Conclusion and Future Scope • References
3. Background • Feature Extraction is the basis of object recognition and behavior understanding and has very broad application and research prospects. • Object tracking is also an important application branch of Computer Vision. The goal of tracking is to recognize target objects from the background and leverage power of open source libraries. • Key objective of the object tracking system is to track the object precisely and in less time using Web Application terminology.
4. Introduction • Angular 7 is a JavaScript framework which makes you able to create reactive Single Page Applications (SPAs). It also provides tool kit for specific Tasks. • Java also provides rich support of Image pre - processing library for, cropping, zooming, and scaling. Also provide an integrate support. • Our Front-End (in Angular 7) and Back-End (in Java 8) helps in delivering the output and make our system more scalable and efficient in comaprison to other monolithic applications.
5. Literature Survey Author Proposed work Advantages Disadvantages Solution Tie Liu (2010) - Template matching -Color spatial method - Edge detection Multiscale contrast background Fails to detect multiple objects Fails when objects in non-linear motion Automation of object detection through system Learning - Open CV Scott McCloskey et al (2011) -Kernel based method - Background mapping Detects Partial occlusion Fails in case of complete occlusion Large Response Time - Bus topology approach - Superposition Estimation - Scalability Table 1. Literature Survey
6. Literature Survey Author Proposed work Advantages Disadvantages Solution Aniruddha Kembhavi et al (2011) - Color probability maps - Partial Least Squares (PLS) Selection of small subset of feature data Performance degradation when illumination decreases Adaboost strong classification Method - Image J Kazuhiro Otsuka et al (2004) Huan Xu et al (2009) Probabilistic framework of explicit multi-view occlusion analysis - Suppresses memory consumption - Robust in case of occlusions - Rendered the system very slow - Increased number of operations on each object Reduction of computations by grouping particles -Fiji Table 2. Literature Survey
7. Algorithms / Approach Client- Server Model 1. The Client-server model is a distributed application structure. 2. Client and server interacts in bi-directional way. 3. Clients do not share any of their resources. 4. When we talk the word Client, it mean capable of receiving information or using a particular service from the service providers (Servers) . 5. Similarly, when we talk the word Servers, It mean a person or medium that serves something. More detail view in Fig 1.
8. Fig 1. Overall Idea Source: wiki
9. System Design
10. Comparison Fig 3. Comparisons Table Source : wiki
11. Dashboards - Visualization Fig 2. User Interface
12. Applications of Image Processing Model • Transport Industry • Astronomical Observation • National Defense • Attendance Monitoring • Surveillance Systems • Remote sensing System
13. Conclusion and Future Scope • Edge detection is the initial step of recognizing object. Edges describe the boundaries of the object that is useful for identification of objects that are presented in the scene such as X-ray image. Edge detection is mostly use in image – segmentation . But all the edge detection techniques are not same. • With an increasing power of modern computing, the concept of computation can go beyond the present limits and in future, image processing technology will advance . • The future trend in remote sensing will towards improved sensors that record the same scene in many spectral channels. Graphics data is becoming important now a days in image processing app1ications. In future image processing technique will play import role in space also.
14. References [1] Angular Official Documentation https://material.angular.io/ , https://angular.io/ [2] Web Application Testing https://www.softwaretestinghelp.com/web-application-testing/ [3] Parsing CSV - APACHE POI https://poi.apache.org/ [4] Posgres Documentation http://www.postgresqltutorial.com/ , https://www.guru99.com/postgresql-tutorial.html https://www.tutorialspoint.com/postgresql/index.htm
15. References [5] M.W. Powell, Java Vision Toolkit (JVT), Univ. of South Florida, FL. Available: http://marathon.csee.usf.edu/~mpowell/jvt/ [6] P.F. Whelan and D. Molloy, “Machine Vision Algorithms in Java: Techniques and Implementation”. New York: Springer Verlag, 2001. [7] B. Morse, “Java Image and Graphics Library (JIGL)”, Brigham Young University, Provo, UT. Available: http://rivit.cs.byu.edu/jigl/ [8] D. Sage and M. Unser, “Easy Java programming for teaching image-processing,” in Proc. IEEE Int. Conf. Image Processing (ICIP’01), Thessaloniki, Greece, 2001, vol. 3, pp. 298–301.