Extraction of Thermos Cup Contour Based on Optimized Edge Feature and Line Detection

In order to solve the problem that the main contour of thermos cups is hard extracted in complex backgrounds, a method, which combines feature extraction and integration of line detection, is proposed. The Faster-RCNN deep neural network optimized by resnet50 is used first to perform preliminary extraction of the thermos cup region in the image. The anisotropic diffusion filtering based on the improvement of gradient contrast is proposed to solve the interference texture in the extracted region, which can effectively suppress textures based on contour preservation. By analyzing the contour characteristics of the thermos cup, the Hough straight line detection algorithm based on the two-way three-neighborhood grouping and the least square are used to extract contours. The results indicate that this method can effectively extract the main contour of the thermos cup in different scenes.

[1]  Р Ю Чуйков,et al.  Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector , 2017 .

[2]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[4]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[5]  S. Lakshmi,et al.  IJCA Special Issue on “Computer Aided Soft Computing Techniques for Imaging and Biomedical Applications” CASCT, 2010. A study of Edge Detection Techniques for Segmentation Computing Approaches , 2022 .

[6]  智一 吉田,et al.  Efficient Graph-Based Image Segmentationを用いた圃場図自動作成手法の検討 , 2014 .

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  George Papandreou,et al.  Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[11]  Gareth Funka-Lea,et al.  Graph Cuts and Efficient N-D Image Segmentation , 2006, International Journal of Computer Vision.

[12]  Yong Wang,et al.  Straight line extraction via multi-scale Hough transform based on pre-storage weight matrix , 2011 .