Texture-based latent space disentanglement for enhancement of a training dataset for ANN-based classification of fruit and vegetables

作     者：Khurram Hameed Douglas Chai Alexander Rassau 

作者机构：School of EngineeringEdith Cowan University270 Joondalup DriveJoondalup WA 6027PerthAustralia 

出 版 物：《Information Processing in Agriculture》 (农业信息处理（英文）)

年 卷 期：2023年第10卷第1期

页      面：85-105页

核心收录：

学科分类：0832[工学-食品科学与工程（可授工学、农学学位）] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081104[工学-模式识别与智能系统] 0901[农学-作物学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 083203[工学-农产品加工及贮藏工程] 

基　　金：Edith Cowan University(ECU) Australia and Higher Education Commission(HEC)Pakistan The Islamia University of Bahawalpur(IUB)Pakistan(5-1/HRD/UE STPI(Batch-V)/1182/2017/HEC) 

主　　题：Information Maximisation(IM) Fruit and vegetables classification Representation Learning(RL) Variational Autoencoder(VAE) Generative Adversarial Network (GAN) Latent space disentanglement 

摘      要：The capability of Convolutional Neural Networks(CNNs)for sparse representation has significant application to complex tasks like Representation Learning(RL).However,labelled datasets of sufficient size for learning this representation are not easily *** unsupervised learning capability of Variational Autoencoders(VAEs)and Generative Adversarial Networks(GANs)provide a promising solution to this issue through their capacity to learn representations for novel data samples and classification *** this research,a texture-based latent space disentanglement technique is proposed to enhance learning of representations for novel data samples.A comparison is performed among different VAEs and GANs with the proposed approach for synthesis of new data *** different VAE architectures are considered,a single layer dense VAE and a convolution based VAE,to compare the effectiveness of different architectures for learning of the *** GANs are selected based on the distance metric for disjoint distribution divergence estimation of complex representation learning *** proposed texture-based disentanglement has been shown to provide a significant improvement for disentangling the process of representation learning by conditioning the random noise and synthesising texture rich images of fruit and vegetables。