This study presents a detailed overview of current technological advances in high-level semantic picture retrieval. It identifies five primary types of state-of-the-art strategies for closing the semantic gap. These are (a) Data Mining approaches for data analysis, data access, and knowledge finding processors to demonstrate experimentally and practically how consistent, capable, and rapid these techniques are for research in a specific subject. To assess the data, a solid mathematical threshold (0 to 1) is set. (b) Image characteristics such as colour, texture, shape, and spatial placement [1]. (b) Measuring similarity and closing the semantic gap (d) A created decision tree presents useful decision-making models that can be taught to help the expert classify images. A data mining and image processing tool is described, and its application to image mining on the job of Hep-2 cell-image categorization is demonstrated. (e) The majority of CBIR system reports only provide qualitative performance measurements based on how similar retrieved images are to a target. Experiment 2 puts Picture Hunter through a more stringent examination in this environment. When the images are given in random order, we first build a baseline for our database by measuring the time it takes to identify an image that is comparable to a target. Integration of salient low-level feature extraction, effective learning of high-level semantics, friendly user interface, and efficient indexing tool are all required to construct a full-fledged image retrieval system with high-level semantics.
Author(S) Details
A. Nanda Gopal Reddy
Mahaveer Institute of Engineering & Technology, Hyderabad, India.
Roheet Bhatnagar
Department of Computer Science and Engineering, Manipal University, Jaipur, Dehmi Kalan, Off Jaipur-Ajmer Expressway, Jaipur, 302026, India.
View Book:- https://stm.bookpi.org/NPER-V4/article/view/5114
No comments:
Post a Comment