Impact of Multi-Feature Extraction on Image Retrieval and classification Using Machine Learning Technique

Abstract

Vast information generated due to the web requires proper mechanisms and tools for efficient management and retrieval of images. This led to the development of an efficient image retrieval system. Image retrieval is the process of retrieving relevant images from a large database. Text-Based Image Retrieval (TBIR) and Content-Based Image Retrieval (CBIR) are the two efficient techniques for image retrieval. It has become an active area of research for image retrieval. Most of the systems are designed with three basic phases in CBIR, i.e. feature extraction, feature selection and similarity matching. Feature extraction can be done based on the colour, shape or texture of the image. The studies conducted so far involve CBIR systems which utilize individual features or only two or more features combined for feature extraction by applying different feature extraction and CBIR techniques. The proposed system illustrates a comparison between the performance of the existing CBIR algorithm with multi-feature extraction using discrete wavelet transform, edge histogram descriptor, sobel operator, moment invariant, histogram-oriented gradient, local binary pattern and classification using Support Vector Machine (SVM) based on the accuracy measures-precision and recall. The experimental results show that multi-feature extraction techniques give better results in some of the individual categories but retrieval results using machine learning is better with respect to average accuracy.

Satellite and Scene Image Classification Based on Transfer Learning and Fine Tuning of ResNet50

“…e experimental evaluation and analysis illustrate that the implemented technique outstrips many state-of-the-art related approaches based on varied hybrid systems. e proposed research achieves the highest accuracy as compared to the state-of-the-art research, thereby outperforming the researches of Li et al [61], Aslam et al [14], SCNN-ELM [61], MKSVM-MIL et al [62], Raja et al [41], Desai et al [42], Yu et al [44], and Shikha et al [43] by 26.16%, 15.74%, 12.68%, 11.8%, 10.34%, 8.8%, 1.02%, and 0.5%, respectively.…”

“…Classification accuracy (%) Inception-V3 [46] 91.1 Feature RCG SVM [60] 93.81 AlexNet [46] 94.2 GoogLeNet [39] 94.31 CaffeNet [39] 95.02 VGG-VD-16 [39] 95.21 ResNet50 97.78 Name of algorithm/model Classification accuracy (%) Li et al [61] 70.84 Aslam et al [14] 81.26 SCNN-ELM [61] 84.32 MKSVM-MIL et al [62] 85.2 Raja et al [41] 86.66 Desai et al [42] 88.2 Yu et al [44] 95.98 Shikha et al [43] 96.5 ResNet50 97…”

Application of Deep Convolution Network Algorithm in Sports Video Hot Spot Detection

“…Correlation between image features can be different. The proposed algorithm calculates the image correlation by defining the distance between two features (Gururaj and Tunga, 2020;Sugiarto et al, 2020;Desai et al, 2021), as detailed below:…”