Food safety inspection using "from presence to classification" object-detection model

With multiresolution decomposition and forest representation of wavelet tra nsforms, we implemented a "from presence to classification" object-detectio n model. Three aspects of this model are studied, First, the presence of an object is quickly detected with fewer data manipulations at the coarsest r esolution; secondly, object classification with high accuracy is fulfilled at the full resolution; and thirdly, the propagation in the coarse-to-fine process is studied in terms of coefficient propagation within a coefficient tree, We applied this model to internal deboned poultry inspection. As soo n as the presence of a hazardous object was detected at a coarse resolution , a signal was actuated to reject the chicken fillet containing foreign inc lusions before packing. Only with small foreign inclusions did we need to r esort to finer resolution analysis. (C) 2001 Pattern Recognition Society. P ublished by Elsevier Science Ltd. All rights reserved.