Improved Content Based Image Retrieval Process Based on Deep Convolutional Neural Network and Salp Swarm Algorithm

Author(s):  
Gangavarapu Venkata Satya Kumar ◽  
P. G. Krishna Mohan

Digital image and medical image retrieval from several repositories are improving gradually, so the capacity of repositories increases rapidly. The semantic space is the main issue on content-based image retrieval (CBIR), which exists among the semantic level as well as increases the data recognized through human and low level visible data obtained through the image. The CBIR system utilizes the deep convolutional neural network (DCNN), which is trained to medical image characterization and the digital image by salp swarm optimization algorithm (SSA). The average classification accuracy for medical image is 86.805%, a mean average precision is 79%, Average Recall Rate (ARR) is 91.7% and [Formula: see text]-measure is 84.9%, are achieved during retrieval task. For image retrieval, the Average Precision Rate (APR) improved from 39%, 40%, 36% and 42.5% to 86.8% and the ARR enhanced from 39.5%, 40.5%, 35.5% and 42.5% to 86.8%. The [Formula: see text]-measure is improved from 39.5%, 40.5%, 35.5% and 42.5% to 86.8% as different with Local tetra patterns (LTrP), LOOP, local derivative pattern (LDP) and local mean differential excitation pattern (LMDeP) separately on Corel-1K dataset. The presented method is most suitable for multimodal digital images and medical image retrieval for various parts of the body.

2017 ◽  
Vol 266 ◽  
pp. 8-20 ◽  
Author(s):  
Adnan Qayyum ◽  
Syed Muhammad Anwar ◽  
Muhammad Awais ◽  
Muhammad Majid

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Shaomin Zhang ◽  
Lijia Zhi ◽  
Tao Zhou

Content-based medical image retrieval (CBMIR) systems attempt to search medical image database to narrow the semantic gap in medical image analysis. The efficacy of high-level medical information representation using features is a major challenge in CBMIR systems. Features play a vital role in the accuracy and speed of the search process. In this paper, we propose a deep convolutional neural network- (CNN-) based framework to learn concise feature vector for medical image retrieval. The medical images are decomposed into five components using empirical mode decomposition (EMD). The deep CNN is trained in a supervised way with multicomponent input, and the learned features are used to retrieve medical images. The IRMA dataset, containing 11,000 X-ray images, 116 classes, is used to validate the proposed method. We achieve a total IRMA error of 43.21 and a mean average precision of 0.86 for retrieval task and IRMA error of 68.48 and F1 measure of 0.66 on classification task, which is the best result compared with existing literature for this dataset.


2020 ◽  
Vol 17 (12) ◽  
pp. 5550-5562
Author(s):  
R. Inbaraj ◽  
G. Ravi

Content-Based Image Retrieval (CBIR) is another yet broadly recognized method for distinguishing images from monstrous and unannotated image databases. With the improvement of network and mixed media headways ending up being increasingly famous, customers are not content with the regular information retrieval progresses. So nowadays, Content-Based Image Retrieval (CBIR) is the perfect and fast recovery source. Lately, various strategies have been created to improve CBIR execution. Data clustering is an overlooked method of hiding formatting extraction from large data blocks. With large data sets, there is a possibility of high dimensionality Models are a challenging domain with both massive numerical accuracy and efficiency for multidimensional data sets. The calibration and rich information dataset contain the problem of recovery and handling of medical images. Every day, more medical images were converted to digital format. Therefore, this work has applied these data to manage and file a novel approach, the “Clustering (MHC) Approach Using Content-Based Medical Image Retrieval Hybrid.” This work is implemented as four levels. With each level, the effectiveness of job retention is improved. Compared to some of the existing works that are being done in the analysis of this work’s literature, the results of this work are compared. The classification and learning features are used to retrieve medical images in a database. The proposed recovery system performs better than the traditional approach; with precision, recall, F-measure, and accuracy of proposed method are 97.29%, 95.023%, 4.36%, and 98.55% respectively. The recommended approach is most appropriate for recuperating clinical images for various parts of the body.


Sign in / Sign up

Export Citation Format

Share Document