James S. J. Lee

Morphologic edge detection

Edge operators based on gray-scale morphologic operations are introduced. These operators can be efficiently implemented in near real time machine vision systems which have special hardware support for gray-scale morphologic operations. The simplest morphologic edge detectors are the dilation residue and erosion residue operators. The underlying motivation for these and some of their combinations are discussed and justified. Finally, the blur-minimum morphologic edge operator is defined. Its inherent noise sensitivity is less than the dilation or the erosion residue operators. Some experimental results are provided to show the validity of these morphologic operators. When compared with the enhancement/thresholding edge detectors and the cubic facet second derivative zero-crossing edge operator, the results show that all the edge operators have similar performance when the noise is small. However, as the noise increases, the second derivative zero-crossing edge operator and the blur-minimum morphologic edge operator have much better performance than the rest of the operators. The advantage of the blur-minimum edge operator is that it is less computationally complex than the facet edge operator.

The digital morphological sampling theorem

Morphological sampling reduces processing time and cost and yet produces results sufficiently close to the result of full processing. A morphological sampling theorem is described which states: (1) how a digital image must be morphologically filtered before sampling in order to preserve the relevant information after sampling; (2) to what precision an appropriate morphologically filtered image can be reconstructed after sampling; and (3) the relationship between morphologically operating before sampling and the more computationally efficient scheme of morphologically operating on the sampled image with a sampled structuring element. The digital sampling theorem is developed first for the case of binary morphology, and then it is extended to gray-scale morphology through the use of the umbra homomorphism theorems. >

Context dependent edge detection and evaluation

Abstract To simulate the edge perception ability of human eyes and detect scene edges from an image, context information must be employed in the edge detection process. To accomplish the optimal use of context, we introduce an edge detection scheme which uses the context of the whole image. The edge context for each pixel is the set of all row monotonically increasing paths through the pixel. The edge detector assigns a pixel that edge state having highest edge probability among all the paths. Based on the same framework, we developed a general robust evaluator for edge detectors. The scheme, based on local edge coherence, does not require any prior information about the ideal edge image and allows any size of neighborhood with which local edge coherence is evaluated on the basis of continuity, thinness, and positional accuracy. The edge evaluator can be incorporated with a feedback mechanism to automatically adjust edge detection parameters (e.g. edge thresholds), for adaptive detection of edges in real images. Experiments indicate the validity of the edge detector and the general edge evaluator. Upon comparing the performance of the context dependent edge detector with the context free second directional derivative zero-crossing edge operator, we find that the context dependent edge detector is superior.

Integration of neural networks and decision tree classifiers for automated cytology screening

A squamous intraepithelial lesion (SIL) detection algorithm has been developed to process conventional Pap smears yielding a superior result (J.S.-J. Lee et al., 1990). The authors compare the object classification performance in an automated cytology screener. It consists of a Sun workstation, a DataCube image processing system, and an automatic stage/optics/illumination system. The system allows automated screening of 10 slides unattended. The main functional modules of the SIL algorithm include: image segmentation, feature extraction, and object classification. The classifiers used include neural network classifiers, statistical binary decision tree classifiers, a hybrid classifier, and the integration of multiple classifiers in an attempt to further improve algorithm performance.<<ETX>>

Context dependent edge detection

To simulate the edge perception ability of human eyes and detect scene edges from an image, context information must be used in the edge detection process. To accomplish the optimal use of the context, the authors introduce an edge detection scheme which uses the context of the whole image. The edge context for each pixel is the set of all row monotonically increasing paths through the pixel. The edge detector assigns a pixel that edge state having highest edge probability among all the paths. Experiments indicate the validity of the edge detector. Upon comparing the performance of the context dependent edge detector with the context free second directional derivative zero-crossing edge operator, the authors find that the context dependent edge detector is superior.<<ETX>>

A novel approach to real-time motion detection

A real-time scheme is introduced that meets a need for fast, reliable, multiple-target motion detection without accurate object velocity or structure measurements. A multiresolution approach decomposes images into a pyramid with several spatial frequency bands to selectively detect motion of interest. Multiple moving targets are detected using a multiple window, coarse-to-fine focus of attention scheme to reconstruct motion energy and search for targets. Real-time sensor motion (translation and rotation) compensations use hierarchical correlation and minimum perturbation. Results are shown for multiple moving targets in FLIR (forward-looking infrared) image sequences from both stationary and moving sensors.<<ETX>>

Binary morphology: working in the sampled domain

A description is given of the relationship between morphologically filtering and then sampling vs. sampling, and then morphologically filtering in the sampled domain. The authors also describe the relationship between morphologically filtering vs. sampling, morphologically filtering in the sampled domain, and then reconstructing. Unlike the standard communication sampling theory where for appropriately low-pass filtered images there is commutivity between sampling and filtering, this is not the case for appropriately morphologically simplified images. The relationship which does exist shows that the commutivity holds to within one sampling interval distance in the unsampled domain and to within two sampling intervals in the sampled domain.<<ETX>>

Improved network inversion technique for query learning application to automated cytology screening

An improved neural network inversion technique that scales the search vector in accordance with the geometry of the problem has been developed. It searches in the direction of the gradient with a vector whose size is inversely related to the size of the gradient. To avoid unlimited growth of the search vector where the gradient is small, an upper bound is set on the size of the search vector. The network was trained by backpropagation and the training was halted when the network produced no error on the training set, where the output was categorized by binary thresholding. The results show the superior performance of the improved method. The technique was applied to automated cytology screening. A set of 400 object feature vectors randomly selected from a large database of 1929 feature vectors served as the initial training data.<<ETX>>

Adaptive Image Processing Techniques

Adaptive image processing schemes can be classified as open-loop, input sensing, invariant-expectation, and model reference systems. Two major adaptive image processing system mechanisms, processing status measurement and parameter adjustment, are described and a multi-resolution approach is developed. The multi-resolution schemes allow efficient adaptive image processing implementation, by enabling coarse-to-fine parameter (operation flow) adjustment in both image and parameter domains. The adaptability and robustness of these techniques is demonstrated on morphologically segmented objects from actual laser radar (range) data.

The Digital Morphological Sampling Theorem

There are potential industrial applications for any methodology which inherently reduces processing time and cost and yet produces results sufficiently close to the result of full processing. It is for this reason that a morphological sampling theorem is important. The morphological sampling theorem described in this paper states: (1) how a digital image must be morphologically filtered before sampling in order to preserve the relevant information after sampling; (2) to what precision an appropriately morphologically filtered image can be reconstructed after sampling; and (3) the relationship between morphologically operating before sampling and the more computationally efficient scheme of morphologically operating on the sampled image with a sampled structuring element. The digital sampling theorem is developed first for the case of binary morphology and then it is extended to gray scale morphology through the use of the umbra homomorphism theorems.