International Journal of Signal and Imaging Systems Engineering (5 papers in press)
A high-throughput system for automated bottle mouth defects inspection
by Bowen Zhou, Yanbin Li, Ming Lu, Lianghong Wu
Abstract: Bottle mouth defects inspection is very important for the production line of beverage and medicine. In this paper, an intelligent inspection system for bottle mouth defects is presented. The linear convection mechanical structure and electrical control system based on Industrial Personal Computer (IPC), motion card and data I/O card are firstly illustrated in detail. Thereafter, a method using the high-speed camera is applied to obtain the bottle mouth image. To find the center of bottle mouth, a novel multi-search-orientation algorithm is proposed, and then the differential detection method based on ring scanning tangent is used to identify the cracks of the bottle mouth. The experimental results show that the detection algorithm is effective and the system is reliable.
Keywords: Visual inspection; Bottle mouth defects inspection; Multi-search-orientation; Circle tangent scan.
Robust and Effective Clothes Recognition System Based on Fusion of Haralick and HOG Features
by Kriti Bansal, Anand Singh Jalal
Abstract: In todays modern era, when the computer has become a necessity of an individual, shopping has shifted from shop to online shopping. We are facilitated with many online sites to search and purchase various types of clothes according to our demands. This kind of clothes classification is used for knowing the name of the cloth that we have seen any movie, serial or anywhere else. It is also used to identify the clothes for our knowledge, to buy it from the market or to discuss with friends. In this paper, we present an efficient method to recognize the clothes in natural scenes as well as in the cluttered background. The proposed approach includes three phases: Extraction of Region of interest (ROI); Construction of Feature Vector; Classification. In the first phase, we detect the face to extract and segment the clothes to mark them as ROI. In the second phase, we have computed feature vector by combining these multiple features for further processing. In the third phase, classification is performed by using Support Vector Machine (SVM) classifier, which classifies the categories of clothes. We have validated the proposed approach using our dataset which contains cluttered background images as well as on Deep Fashion standard dataset. The proposed method successfully resolved the issues of misclassification of clothes in the cluttered background with different illumination conditions. Experimental results show that the proposed technique successfully achieved 88.36% clothes recognition rate.
Keywords: Clothes recognition; Histogram of Oriented Gradients (HOG); Haralick.
Special Issue on: Future Directions in Signal and Image Systems
Improvement of Image Compression Approach using Dynamic Quantization based on HVS
by Mourad Rahali, Habiba Loukil, Med Salim Bouhlel
Abstract: Digital-image compression can reduce the overall volume of the image by keeping the original image with the minimum degradation in the level of the reconstructed image quality; in other words, here, we speak about compression with loss. This work comes up with an improvement in an image compression method using the discrete wavelet transform (DWT) and neural networks. To improve this technique, we have added a new phase based on the Human Visual System (HVS) and the Weber-Fechner law to dynamically quantify the image signal. Such a new phase can improve the quality of compression by dynamically quantifying each pixel value of the original image compared to the values of the neighbor pixels according to a luminance detection threshold. This threshold is known as Weber constant.
Keywords: Image compression; Human Visual System; Dynamic Quantization; Weber-Fechner law; Weber constant.
HYBRID APPROACH FOR HUMAN COMPUTER INTERACTION USING CARDIAC ECG SIGNAL DATA CLASSIFICATION SYSTEM
by Selvakumar Subramaniam, Hannah Inbarani, SENTHIL KUMAR
Abstract: In the previous couple of years numerous frameworks for taking decision support from samples were established. As various frameworks permit distinctive kinds of results while classification new cases, it is hard to fittingly assess the frameworks' classification control in examination with other order frameworks or in correlation with human specialists. Order precision is normally utilized as a measure of classification execution. A novel hybrid Improved Monkey based search (IMS) and support vector machine (SVM) technique for the location of arrhythmia in long span ECGs is proposed. It incorporates noise handling, include extraction, rule based beat classification, sliding window arrangement and heart arrhythmia recognizable proof, all coordinated in a grouping system. It can be executed continuously and can give clarifications to the analytic choices got. The strategy was tried on the UCI ECG database and high scores were acquired for both sensitivity and specificity (98.1% and 98.5% correspondingly using collective accuracy gross information, and 98.8% using aggregate average statistics.
Keywords: ECG; Cardiac arrhythmia; IMS; SVM; Classification.
ECHOCARDIOGRAPHY IMAGE SEGMENTATION USING FEED FORWARD ARTIFICIAL NEURAL NETWORK (FFANN) WITH FUZZY MULTI-SCALE EDGE DETECTION (FMED)
by Mohamed Shakeel P, Baskar S
Abstract: In the medicinal filed, the Echocardiography image segmentation is one of the signification process is actually describes about segment out the inner and outer walls or other parts of the organ boundaries. However, this kind of segmentation process is one of the difficult for physicians because of inexperience or subject specialists with the previous case. So as to enhance the cardiac image segmentation accuracy and to minimize the segmentation time has to develop a reliable and efficient segmentation system. Hence, in this paper proposes a machine learning method such as neural networks for cardiac image segmentation process which has shown high potential to be employed in the segmentation process. Initially in this work obtain the object images from input video then the Feed Forward Artificial Neural Network (FFANN) is utilized for process of image segmentation. After the segmentation process Fuzzy Multi-scale Edge Detection (FMED) process applied for detected the segmented edges which is used for defined the detected texture boundary with the help of FFANN weights. Experimental results show an efficient learning capacity of FFANN and this work deals with the segmentation of ultrasound images using MATLAB implementation
Keywords: Echocardiography image segmentation; Ultrasound Images; Feed Forward Artificial Neural Network (FFANN); Fuzzy Multi-Scale Edge Detection (FMED).