Have We Solved Edge Detection? A Review of State-of-the-Art Datasets and DNN Based Techniques
Open Access
- 1 July 2022
- journal article
- review article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 70541-70552
Abstract
Recent Deep Neural Networks (DNNs) based edge detection methods claim to beat human performance on small scale datasets like BSDS500. But is the problem of edge detection really solved? To answer this question, we review the existing dataset limitations as well as the generalization capabilities of the proposed architectures. To this end, we develop a Synthetic Textured Masks Dataset (STMD) that contains 28,000 grayscale images. The performance of several edge detection methods is severely degraded on STMD. To further validate these results we propose a baseline Single Scale Feed Forward Edge Detector (SFED), which is a simple 9-layer feed-forward convolutional neural network with no pooling layers. The performance of SFED is better than most state-of-the-art architectures on BSDS500 and is superior to all the compared architectures on STMD. These results show that most of the architectural advancements of existing architectures are at the cost of generalizability where if we change the dataset set distribution (both training and testset), the performance becomes significantly degraded and therefore the problem of edge detection is still far away from being solved. There are also severe limitations of existing datasets in the field, and STMD provides a framework for designing and testing better edge detection architectures for novel application areas, such as, medical imaging and self-driving cars.Keywords
Funding Information
- Syed Babar Ali School of Science and Engineering (SBASSE), Lahore University of Management Sciences, Dean’s Pool
- Natural Science Foundation of China (61850410535)
This publication has 38 references indexed in Scilit:
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A Level Set Approach to Image Segmentation With Intensity InhomogeneityIEEE Transactions on Cybernetics, 2015
- Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images2013
- Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Logarithmic edge detection with applications2007
- An adaptive edge detection based colorization algorithm and its applications2005
- Detecting faces in images: a surveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Motion-based segmentation and contour-based classification of video objects2001
- On the accuracy of the Sobel edge detectorImage and Vision Computing, 1983