Nuclei segmentation is an important pre-processing step for any vision based cytopathological diagnostic system which extracts information from nuclei to perform tasks such as cancer detection. A cell nuclei segmentation pipeline should be robust, accurate and fast. We propose a deep learning based model, Contour-Aware Residual W-Net (WRC-Net), which consists of double U-Net, [5] or W-Net. The first U-Net learns to predict nuclei boundaries and the second generates the segmentation map. Our model can accurately segment a 128x128 dimensional image in less than 0.05s. Our model can learn from a very limited training data with as low as a single training image. We tested our model on real HE (Hematoxylin and Eosin) stained cell images and it showed better overall performance against previous state-of-the-art nuclei segmentation methods.

Cytology is one of the decisive factors for the early detection of cancer. It is necessary to have a certain number of years of experience to be able to screen tumor cells for cytodiagnosis. However, this diagnosis has poor objectivity because there are so many parts that the judge’s experience and skill is responsible for. In this paper, we present a new method to extract cell nuclei from HE stained images generally used cell staining for Creation of digitized objective indicators in cytology. Our method extracts cell nuclei using combining the input image and the image previously prepared by SVM. Features used in SVM are automatically generated from CNN. Results are demonstrated by experiments using the real images and its ground truths.

No abstract available.

In this paper we investigate the performance of a technique for face recognition based on the computation of 25 local autocorrelation coefficients. We use a large database of 11,600 frontal facial images of 116 persons, organized in training and test sets, for evaluation. Autocorrelation coefficients are computationally inexpensive, inherently shift-invariant and quite robust against changes in facial expression. We focus on the difficult problem of recognizing a large number of known human faces while rejecting other, unknown faces which lie quite close in pattern space. A multiresolution system achieves a recognition rate of 95%, while falsely accepting only 1.5% of unknown faces. It operates at a speed of about one face per second. Without rejection of unknown faces, we obtain a peak recognition rate of 99.9%. The good performance indicates that local autocorrelation coefficients have a surprisingly high information content.

We describe and evaluate information fusion by fuzzy integration in a robust, high performance face recognition system. The system uses fuzzy integrals to combine classifiers operating at different image resolutions. Recognition is carried out by distance classification of transformed vectors of local autocorrelation coefficients. The transformation is determined by linear discriminant analysis. A large database of 11,600 images of 116 persons is used to determine the system performance. After being trained to recognize 60 persons, it is tested on images of all persons in the database. Both training and test stages use 50 images of each person. Under two different training schemes, it achieves peak recognition rates of 98.4% and 97.9%, respectively, accepting only 1.6% and 2.4% of the unknown faces. This exceeds the performance of any of the individual classifiers by at least 10%. Moreover, it exceeds earlier results obtained by multiple resolution averaging on the same database by at least 1.0%.