Detection of Contamination Defect on Ice Cream Bar Based on Fuzzy Rule and Absolute Neighborhood

The contamination proposed in this paper is a defect on the surface of ice cream bar,which is a serious security threat.So it is essential to detect this defect before launched on the market. A detection method of contamination defect on the ice cream bar surface is proposed,which is based on fuzzy rule and absolute neighborhood feature. Firstly,the ice cream bar surface is divided into several sub-regions via the defined adjacent gray level clustering method. Then the alternative contamination regions are extracted from the sub-regions via the defined fuzzy rule. At last,the real contamination regions are recognized via the relationship between absolute neighborhood gray feature and default threshold. The algorithm was tested in the self-built image database SUT-D. The results show that the accuracy of the method proposed in this paper is 97.32 percent,which increases 2.68 percent at least comparing to the other typical algorithms. It indicates that the superiority proposed in this paper,which is of actual use value.

A Study of Feature Stability of Contact-Less Imaging Based on Palm Vein

Palm vein hidden under the skin and its distribution feature is hard to be stolen, which makes the palm vein recognition to be a high security biometric authentication method. Contact-less palm vein imaging can avoid the spread of disease, thus expanding the application range of palm vein biometric authentication devices. However, due to the different un-derstanding of the right imaging position and the change of fingers open degree, contact-less palm vein image acquisi-tion led to a certain degree of translation, rotation, scaling and shear, that is, the image deformation. Image deformation causes the imaging feature unstable. In this paper, the effect of image deformation to the stability of palm vein features is studied by some similarity parameters. First, feature points in the palm were marked, contact-less imaging and con-tact imaging of palm vein were acquired. Then, this paper calculated the similarity parameters of the contact-less imag-ing to contact imaging and gave corresponding analysis. Experimental results show that contact-less palm vein imagingwas stable, and derived the linear regression equation of relationship between sample space and the recognition rate: y =?0.000903x + 1.0332, coefficient of determination R2 = 0.9824. This research provided effective and detailed data to the study of contact-less palm vein recognition and gave powerful support to contact-less multi-feature fusion recogni-tion based on hand.

Detection of Sunken Defects on the FPC Trace

Trace is the important composition structure of printed circuit board,w hich connects the devices,it is also the module that taking up the highest proportion,thus,it is the major testing target of quality assurance. The sunken defects proposed in this paper is a w idth abnormity defect on the FPC trace,w hich w ould cause the latent open circuit defect and affect the electrical function of circuit. The problem of flexible deformation and w idth difference make the FPC trace detection harder. Therefore,this paper proposed a detection scheme combined w ith linear masks and circle distribution characteristic. Firstly,this scheme preprocessed the acquired FPC image,divided the trace into several sub-regions and obtained the line w idth values of each trace transverse section. Then the line w idth sequences w ere searched w ith the linear difference template of gray scale. Thus,the sunken defects alternative positions w ere located. Lastly,the circle distribution characteristic is defined to identify the real defect areas from the alternative regions acquired from the previous step. Thus,the detection of sunken defects on the FPC trace w as accomplished.The algorithm w as tested in the self-built image database,w hich show s the better detection performance than the other typical algorithms.