Classification of Fashion Article Images Based on Improved Random Forest and VGG-IE Algorithm

Abstract

In classification of fashion article images based on e-commerce image recommendation system, the classification accuracy and computation time cannot meet the actual requirements. Herein, for the first time to our knowledge, we present two diverse image recognition approaches for classification of fashion article images called random-forest method based on genetic algorithm (GA-RF) and Visual Geometry Group-Image Enhancement algorithm (VGG-IE) to solve classification accuracy and computation time problem. In GA-RF, the number of segmentation times and the decision trees are the key factors affecting the classification results. Improved genetic algorithm is introduced into the parameter optimization of forests to determine the optimal combination of the two parameters with minimal manual intervention. Finally, we propose six different Deep Neural Network architectures, including VGG-IE, to improve classification accuracy. The VGG-IE algorithm uses batch normalization and seven kinds training-data augmentation for ease and promotion of learning process. We investigate the effectiveness of the proposed method using Fashion-MNIST dataset and 70[Formula: see text]000 pictures, Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 10 categories of image recognition, our VGG algorithm has the shortest computational time when it satisfies certain classification accuracy. VGG-IE approach has the highest classification accuracy.

Artificial Intelligence in Business-to-Customer Fashion Retail: A Literature Review

“…FastkNN [152] FCNN [56] FNN [32] Fuzzylogic [106,113] GAN [71,75,99,129,134,141,155,251] GA-RF [65] GaussianMixtureModels [109,118] gradientboostingdecisiontree [42] GraphCNN [40,122] GraphDCNN [89] GRU [230] GSN [87] H-CNN [39,157] HOG [153] HypergraphNN [80] Imageprocessing [119,120,130,132,135,136,147] k-center [117] k-means [114,203,232,244] k-medoids [115] Kneser-Ney [34] kNN [54,137,222,235,237,250] LAC [107,116] Lassoregression …”

Predicting the language of depression from multivariate twitter data using a feature‐rich hybrid deep learning model

“…LinearSVC is a support vector with a kernel parameter set to linear that tackles overlying and scattered data points preventing hyperplane formation. It employs multidimensional space and attempts to find the best hyperplane given a training dataset. RF classifier : The RF classifier 12 is an ensemble method comprised of several individual decision trees determining the final outcome. The ensemble of such trees votes for the most prevalent class.…”

“…This aids in increasing the training speed of hybrid model while maintaining its accuracy. Once a filter F is iterated across the whole matrix, the extracted feature map is presented in Equation (12).…”

“…The RF classifier 12 is an ensemble method comprised of several individual decision trees determining the final outcome. The ensemble of such trees votes for the most prevalent class.…”

“…We presented a depression prediction paradigm based on tweets broadcasted by mentally ill people. The study's main objective is to design a hybrid DL model for predicting the sentiments of online users who are depressed and to perform two types of comparative analysis: a. with four widely used state-of-the-art ML models, namely Naïve Bayes classifier (NB), 10 linear support vector classification (LinearSVC), 11 random forest (RF), 12 and decision tree (DT). 13 b. with hybrid DL-based models, namely CNN-biLSTM, 14 TCN (temporal convolution network)-LSTM, 15 TCN-biLSTM.…”