Abstract: The invention is a system and method for constructing a rolled surface image from a set of partial surface images. A sequence of individual partial surface images is acquired as an object is progressively rolled across the surface of an imaging device. The imaging device is configured so that only that part of the object's surface which is in close proximity is imaged. To produce a complete rolled surface image, i.e. a composite image, the value of each pixel of the composite image is derived by performing a suitable pixel operation on the set of corresponding pixels in the input partial surface images. This is possible because each partial image is represented as a fixed size and each pixel in each of the partial images has a unique position in the partial image. The system can also directly produce a list of salient surface features. Localized features are extracted from each individual partial image whereas other specific attributes of each image are ignored.

Abstract: The present system and apparatus use image processing to recognize object size with a scene. The system includes novel image processing apparatus and method to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: The present system and apparatus uses image processing to recognize object size within a scene. The system includes novel image processing apparatus and methods to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: A method to hide small messages in a wavelet compressed fingerprint image is presented. The method is characterized by random placement of the message bits in the compressed and quantized indices. The compressed image can be decompressed by any certified decompressor without any visible difference. However, the decoder aware of the decompression can only retrieve the hidden message in the image and additionally decompress the image without any error in pixel values.

Abstract: The present system and apparatus uses image processing to recognize object size within a scene. The system includes novel image processing apparatus and methods to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: One or more sets of prototype descriptions for a number of classes of objects stored on a computer database are maintained. These prototypes are used as a basis for identifying the class of a presented object. A trainer determines when a new prototype is required to be added to the database based on current match results. This allows the system to be trained to recognize items in classes that deviate significantly from the items that were initially used to determine the classification rules. A determination is made about which prototypes can be deleted on the basis of their match histories. This allows the system to automatically optimize itself to work with a bounded collection of prototypes. In addition, it allows the system to track variations in class characteristics over time and adjust the corresponding set of prototypes appropriately.