The images of steel surfaces are generally textural images. There are different texture analysis methods to extract features from these images. In those methods using multi-scale/multi-directional analysis, Gabor filters are used for feature extraction. In this paper, w More
The images of steel surfaces are generally textural images. There are different texture analysis methods to extract features from these images. In those methods using multi-scale/multi-directional analysis, Gabor filters are used for feature extraction. In this paper, we extract texture features using the optimum Gabor filter bank. This filter bank is designed in a way that diverse filtering frequency and orientation will allow it to extract considerable amounts of texture information from the input images. We also introduce a new method called Gabor composition for segmentation and defect detection of steel surfaces. In this method, using two different algorithms, the input image is decomposed into detail images using an appropriate Gabor filter bank and then selected detail images are re composed. The created feature map illustrates the defective areas well. By calculating data distribution of detail images and comparing them, the second method of Gabor composition can accomplish segmentation without needing the normal images and the number of detail images to re-compose. Furthermore, we did different tests towards optimizing of segmentation by means of classifiers. Using a K-means classifier and adding gray levels to the extracted features, complete the segmentation procedure. The experimental results show that the Gabor composition method in most of the tests has got better defect detection performance than the ordinary K-means classifier and the standard wavelet method; also the Second method of Gabor composition has got the best performance over all.
Manuscript profile
Object boundaries detection is one of the interesting subjects in computer and image processing. Active contour models are one of the popular methods in object detection and segmentation. This paper presents a new method for segmentation of texture object by means of pa More
Object boundaries detection is one of the interesting subjects in computer and image processing. Active contour models are one of the popular methods in object detection and segmentation. This paper presents a new method for segmentation of texture object by means of parametric active contour. In this proposed method, by adding a balloon energy to energy function of the parametric active contour model, the detection and segmentation of textured object against textured background would be achieved. In this method, texture feature of contour and object points are calculated by contourlet transform. Then by comparing these features with texture feature of target object, which are available as prior information, movement direction of balloon is defined, whereupon contour curves are expanded or contracted in order to adapt to the target boundaries. Experimental results demonstrate that the active contour based on contourlet (Contourlet-ACM) has higher segmentation accuracy than the active contour based on moment (Moment-ACM) and active contour based on DWHT (DWHT-ACM).
Manuscript profile
This paper aims to present a cloud-based learning agent-oriented approach for verification of the pacemaker behavior by monitoring and heart rate adjustment of an arrhythmic patient. In case of the pacemaker failure or inappropriate heart rate generation, the patient is More
This paper aims to present a cloud-based learning agent-oriented approach for verification of the pacemaker behavior by monitoring and heart rate adjustment of an arrhythmic patient. In case of the pacemaker failure or inappropriate heart rate generation, the patient is put at risk. Using the proposed approach, one can directs the pacemaker rate to correct one when it is incorrect. Using a learnable software agent, the proposed approach is able to learn un-predefined situations and operates accordingly. The proposed approach is cloud based meaning that it sends a message through cloud in case of a critical situation. After determining the patient heart rate by pacemaker, the proposed method verifies this rate against the predefined physician suggestion and automatically corrects it based on a reinforcement learning mechanism if there is some conflict. The proposed method was implemented and installed on a tablet as a patient mobile device for monitoring the pacemaker implanted in the patient chest. The contrast between results of our approach and expected results existing in the dataset showed our approach improved the pacemaker accuracy until 13.24%. The use of the software agent with reinforcement learning is able to play a significant role in improving medical devices in case of critical situations.
Manuscript profile
