Multi-Scale Auto-Encoder for Edge Detection

Abstract

A multi-scale encoder algorithm is proposed for image edge detection, which takes the autoencoder as basic backbone structure. Three auto-encoders, each is responsible for processing an image of one scale, are organized together to perform image-to-image prediction by combining all multi-scale convolutional features. Taking the advantage of the multi-scale strategy and self-attention mechanism, the algorithm detects image edges from coarse to fine gradually, and succeeds in detection the edges missed easily in other works. There are two types of skip connections designed in the model structure. One is connected between encoder and decoder within an auto-encoder, worked as the residual function, the other is between auto-encoders, providing multi-scale knowledge about the edges. The loss function is composed of cross-entropy function and Dice coefficient term which is used to handle imbalanced training data. Experimental results evaluated from BSDS500 and BIPED datasets show the algorithm achieves scores of 0.847, 0.858, 0.884 on ODS, OIS, AP indices and output high-quality edges.

Combining Convolutional Neural Networks for Fungi Classification

“…The categorization and identification of traditional patterns include mathematical and statistical simulations that can analyze various qualities or forms. The techniques described in this study include two main approaches: image matching and the generation of color levels or pattern analysis [1] [2]. The primary premise of these strategies is to establish data levels that exhibit a tight relationship, usually within a specific range.…”