论文信息 - Recognition of overlapping particles in granular product images using statistics and neural networks

Recognition of overlapping particles in granular product images using statistics and neural networks

Abstract Image analysis can be used to characterize granular populations in many processes in the food industry or in agricultural engineering. Either global or individual parameters can be extracted from the image. However, granular products may agglomerate on the image, bringing bias measurements of individual parmeters: products which agglomerate have to be recognized. This is done by a combination of image analysis (to pre-process and extract features), statistical methods (to reduce information) and neural network techniques (to take decisions).

[1] Shashi Shekhar,et al. Generalization Performance of Feed-Forward Neural Networks , 1992 .

[2] Richard P. Lippmann,et al. An introduction to computing with neural nets , 1987 .

[3] Brian D. Ripley,et al. Statistical aspects of neural networks , 1993 .

[4] Paul Robert,et al. Characterisation of powders by video image analysis , 1991 .

[5] Kunihiko Fukushima,et al. Recognition and segmentation of connected characters with selective attention , 1993, Neural Networks.

[6] Mary M. Galloway,et al. Texture analysis using gray level run lengths , 1974 .

[7] Philippe Courcoux,et al. Stepwise canonical discriminant analysis of continuous digitalized signals: Application to chromatograms of wheat proteins , 1990 .

[8] G. Rabatel,et al. Plant grading by vision using neural networks and statistics , 1993 .

[9] Ren C. Luo,et al. The analysis of natural textures using run length features , 1988 .

[10] Calvin C. Gotlieb,et al. Texture descriptors based on co-occurrence matrices , 1990, Comput. Vis. Graph. Image Process..

[11] A. Resurreccion,et al. Applications of multivariate methods in food quality evaluation , 1988 .

[12] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.