A pattern recognition and adaptive approach to quality control

The present paper describes some quality control tools that develop an interactive and on-line evaluation of industrial products. These tools use pattern recognition techniques in a dynamic way, it means, they control the variations of critical characteristics of industrial products during their effective use. They also make an adaptive evaluation because considers the characteristics of each product under analysis. The tools generate a dynamic and well structured model. The operation of the model considers a set of images of the product or parts of them during some specific use or specific moment. Using a Pattern Recognition Process, the images of the product or some parts of them are captured and they are associated to some special matrices. The model then analyses the properties of these images by evaluating the properties each corresponding matrix have. This process allows determining a set of values which describe the variations the product is showing during its use. We gave so a model which develops a continuous evaluation of product quality. Thus, the model checks whether the variations of the characteristic under study are acceptable or not, considering a set of limits defined by procedures which take into consideration particularities of the product being studied. Thereto, the model itself determines which reference values are to be used to evaluate such variations. In the case of monochromatic analyses, the model seeks to define reference parameters for defect detection using maximum variation limits of gray levels on the product surface (this makes possible to detect the presence of a crack, for instance). In the case of polychromatic analyses, having established a specific property (such as intensity, saturation or chromatic hue), the model determines the most adequate values for that property. Variations complying with those parameters are considered to be acceptable. The top and bottom values of the acceptable variations can accurately define product design characteristics from the effective practical use the product is supposed to have. This paper describes the model, reports the most usual situations for its use, discusses practical cases where it was used and provides a critical evaluation of the results obtained.

[1]  Chen-Chien James Hsu,et al.  Image ruler and its applications in distance and area measurement , 2007 .

[2]  Adnan Khashman,et al.  A Novel Thresholding Method for Text Separation and Document Enhancement , 2007 .

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

[4]  Shu-Kai S. Fan,et al.  Optimal multi-thresholding using a hybrid optimization approach , 2005, Pattern Recognit. Lett..

[5]  J SWETS,et al.  Decision processes in perception. , 1961, Psychological review.

[6]  Omid Khayat,et al.  An overview on model-based approaches in face recognition , 2008 .

[7]  Xianghua Yao,et al.  Iris recognition based on multialgorithmic fusion , 2007 .

[8]  C. Hung,et al.  Melancholia diagnosis based on CMAC neural network approach , 2007 .

[9]  Cheng-Chuan Chen,et al.  Outdoor image recording and area measurement system , 2007 .

[10]  Azriel Rosenfeld,et al.  Histogram modification for threshold selection , 1977 .

[11]  Azlinah Mohamed,et al.  Online signature slant feature identification algorithm , 2008 .

[12]  F. Sassani,et al.  Application of fuzzy lead time to a material requirement planning system , 2007 .

[13]  Ian J Murray,et al.  Perceived shifts in saturation and hue of chromatic stimuli in the near peripheral retina. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[14]  King-Sun Fu,et al.  Syntactic Pattern Recognition And Applications , 1968 .

[16]  J Bowe,et al.  Total quality management. , 1992, Contemporary longterm care.

[17]  Li Xiaojuan,et al.  A novel bacteria classification scheme based on microscopic image analysis , 2007 .

[18]  E. R. Davies,et al.  Machine vision - theory, algorithms, practicalities , 2004 .

[19]  D. Andina,et al.  Proceedings of the 10th WSEAS international conference on Signal processing, computational geometry and artificial vision , 2004 .

[20]  T. W. Ridler,et al.  Picture thresholding using an iterative selection method. , 1978 .

[21]  Intelligent controlling water dispersal: comparison between mamdani and conventional approach , 2007 .

[22]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[23]  Kanti V. Mardia,et al.  A Spatial Thresholding Method for Image Segmentation , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Hui-Fuang Ng,et al.  Automatic thresholding for defect detection , 2004, Third International Conference on Image and Graphics (ICIG'04).

[25]  R. C. Thomas,et al.  Computer Vision: A First Course , 1988 .

[26]  Omid Khayat,et al.  Image classification using principal feature analysis , 2008 .