An effective multiple visual features for Content Based Medical Image Retrieval

Abstract

In the medical field accurate diagnosis is very crucial for successful treatment. With the rapid development of technology, the ever increasing quantity of medical images is produced in hospitals for diagnosing. Content-Based Image Retrieval (CBMIR) is a technique retrieves similar medical images from large database using visual features such as color, texture and shape. This paper focuses a novel method to increase the performance of Content Based Medical Image Retrieval System (CBMIRS). A multiple features vector gives betterquality performance as compared to a single feature. This paper presents a new approach which takes the advantages of each individual feature. The content of the image extracted with the help of texture and region based shape descriptor, which have better features representation capabilities and are more robust to noise. The texture features are extracted with the help of Gabor filter and chebichef Moments used for Shape features extraction. The similar medical images will be retrieved by comparing the feature vector of the query image with the corresponding feature vectors of the data base images using Euclidian distance as a similarity measure. Experimental results show that proposed method achieves highest retrieval performance in comparison with individual feature based retrieval system.

Enhanced Visual Analytics Technique for Content-Based Medical Image Retrieval

“…Whereas the VAMIR process gives additional imminent keen on image correlation, a user must still inspect the real figure to determine the complete qualities of an instance (e.g., stages of infection). To determine whether an image obtained by feature space exploration meets the supplied search purpose, a connection between both the conceptual representation and the real image is provided [8].…”

Effective Diagnosis and Treatment through Content-Based Medical Image Retrieval (CBMIR) by Using Artificial Intelligence

“…Although many researchers have studied the CBMIR by using handcrafted features [14,15,16,17,18,19,20,21,22,23,24,25,26], the overall performance of the existing systems is still low due to the growing heterogeneous medical images of multiclass database and conventional ML techniques. These techniques are unable to decrease the “semantic gap,” which is the information lost by converting an image (i.e., a high-level representation) into its visual features (i.e., a low-level representation) [27].…”