Automated Tongue Diagnosis: A Deep Autoencoder Neural Network and Clustering-Based Image Segmentation Approach

Abstract

Automatic tongue image segmentation and tongue image classification are two crucial tongue characterization tasks in traditional Chinese medicine (TCM). Due to the complexity of tongue segmentation and fine-grained traits of tongue image classification, both tasks are challenging. Fortunately, from the perspective of computer vision, these two Tasks are highly interrelated, making them compatible with the idea of Multi-Task Joint learning (MTL).By sharing the underlying parameters and adding two different task loss functions, an MTL method for segmenting and classifying tongue images is proposed in this paper. Moreover, two state-of-the-art deep neural network variants (UNET and Discriminative Filter Learning (DFL)) are foused into the MTL to perform these two tasks. To the best of our knowledge, our method is the first attempt to manage both tasks simultaneously with MTL. We conducted extensive experiments with the proposed method. The experimental results show that our joint method out performs the existing tongue characterization methods. The process of tongue diagnosis by extracting meaningful features from tongue images and segmenting the relevant regions for analysis. The deep auto encoder neural network is employed to learn a compact representation of tongue images by encoding and decoding the input data.