Clothes Retrieval Using M-AlexNet With Mish Function and Feature Selection Using Joint Shannon’s Entropy Pearson’s Correlation Coefficient

The online retrieval of clothes-related images is crucial because finding the exact items, like the query image from a large amount of data, is highly challenging. However, significant clothes image variations degrade visual search retrieval accuracy. Another problem with retrieval accuracy is the high dimensions of feature vectors obtained from pre-trained deep CNN models. This research aims to enhance clothes retrieval training and test accuracy by using two different means. Initially, features are extracted using the modified AlexNet (M-AlexNet) with slight modification. The ReLU activation function is replaced with a self-regularized Mish activation function because of its non-monotonic nature. The M-AlexNet with Mish is trained on the CIFAR-10 dataset using the SoftMax classifier. Another contribution is to reduce the dimensions of feature vectors obtained from M-AlexNet. The dimensions of features are reduced by selecting the top
$k$
-ranked features and removing some of the different features using the proposed Joint Shannon’s Entropy Pearson Correlation Coefficient (JSE-PCC) technique to enhance the clothes retrieval performance. To calculate the efficacy of suggested methods, the comparison is performed with other deep CNN models such as baseline AlexNet, VGG-16, VGG-19, and ResNet50 on DeepFashion2, MVC, and the proposed Clothes Image Dataset (CID). Extensive experiments indicate that AlexNet with Mish attains 85.15%, 82.04%, and 83.65% accuracy on DeepFashion2, MVC, and 83.65% on CID datasets. Hence, M-AlexNet and the proposed feature selection technique surpassed the results with a margin of 5.11% on DeepFashion2, 1.95% on MVC, and 3.51% on CID datasets.