This paper presents a method to identify the edges and corners of clothes in an image using image processing methods. In clothes manipulation, it is important for the GUI program to identify the shape of clothes before spreading and folding. The first step for clothes manipulation is that the robot needs to grab two real corners so the clothes can be spread easily. The computer vision system becomes an important part in finding the corner of clothes. With the help of image processing, the corner of clothes can be identified for the robot to spread and fold the clothes. This method to identify the corner of clothes in the image is by applying certain image processing methods. Some basic morphological operations are used to filter the image captured in order to reduce the noise and disturbance and also extract the essential data from the image for further processing. The purpose of using this method is to identify the pixel in the image which is potentially represented as a corner of the clothes and become a starting point for the robot in clothes manipulation.

Identifying corners of clothes using image processing method

A new method of angle detection based on the topological median filter is proposed. Topological opening operator is used to detect corners and Topological closing operator is used to calculate the corner angles on gray level images.

Gray level topological angle detection of high curvature points

In the image processing of 3D precision measurement field, the traditional edge detection algorithms cannot find all the relevant edges which hide the height information. A quaternion-vector edge detecting approach of color image is presented to realize the micro-height-measurement by using the color fringes encoding structure light. The proposed edge detection procedure consists of two steps: firstly, the color similarity function is designed based on the quaternion-vector theory; secondly, the horizontal and vertical edges are distinguished based on the function presented in the first step. The characteristic points, as well as their height fringes, are then determined, and the height values are thus obtained. Finally, experiments are performed to show the effectiveness of the proposed approach.

A Quaternion-Vector Edge Detecting Approach of Height-Measurement in Complex Environment

A new corner detection algorithm based on the topological median filter is proposed. Topological quasi dilation and erosion operators with circular structuring element are used to detect the corners on gray level images.

Ibrahim Kivanc Cihan

Papers

Gray Level Topological Corner Detection

Topology Based Corner Detection

Gray level topological angle detection of high curvature points