Texture Classification in Extreme Scale Variations Using GANet

Restored texture segmentation using Markov random fields

Texture segmentation plays a crucial role in the domain of image analysis and its recognition. Noise is inextricably linked to images, just like it is with every signal received by sensing, which has an impact on how well the segmentation process performs in general. Recent literature reveals that the research community has started recognizing the domain of noisy texture segmentation for its work towards solutions for the automated quality inspection of objects, decision support for biomedical images, facial expressions identification, retrieving image data from a huge dataset and many others. Motivated by the latest work on noisy textures, during our work being presented here, Brodatz and Prague texture images are contaminated with Gaussian and salt-n-pepper noise. A three-phase approach is developed for the segmentation of textures contaminated by noise. In the first phase, these contaminated images are restored using techniques with excellent performance as per the recent literature. In the remaining two phases, segmentation of the restored textures is carried out by a novel technique developed using Markov Random Fields (MRF) and objective customization of the Median Filter based on segmentation performance metrics. When the proposed approach is evaluated on Brodatz textures, an improvement of up to 16% segmentation accuracy for salt-n-pepper noise with 70% noise density and 15.1% accuracy for Gaussian noise (with a variance of 50) has been made in comparison with the benchmark approaches. On Prague textures, accuracy is improved by 4.08% for Gaussian noise (with variance 10) and by 2.47% for salt-n-pepper noise with 20% noise density. The approach in the present study can be applied to a diversified class of image analysis applications spanning a wide spectrum such as satellite images, medical images, industrial inspection, geo-informatics, etc.

Swarm optimization based texture classification in extreme scale variations

Texture analysis has remained a remarkably trendsetting and productive field of research in the last two decades. There has been much progress, but the impact of illumination changes on automated texture classification and segmentation has gained very less focus. Research work carried out in the field of texture identification frequently focuses on the identification of textures with intraclass changes including illumination, rotation, viewpoint and small scale variations. Consequently, variations in texture owing to modifications in scale constitute among the ones that are difficult to manage. In this research work, as the first step, the classification of textures due to vast changes in scale is studied. In order to deal with this problem, first the solution is introduced and then the scale changes are reduced based on the predominant patterns in the texture. Inspired by the challenges imposed by this issue, a novel swarm intelligence approach known as Ant Colony Optimization (ACO) algorithm is introduced for modifying the components in the hidden layers used during the network training, for the extraction of more useful semantic texture patterns.

A Class-Independent Texture-Separation Method Based on a Pixel-Wise Binary Classification

Texture segmentation is a challenging problem in computer vision due to the subjective nature of textures, the variability in which they occur in images, their dependence on scale and illumination variation, and the lack of a precise definition in the literature. This paper proposes a method to segment textures through a binary pixel-wise classification, thereby without the need for a predefined number of textures classes. Using a convolutional neural network, with an encoder–decoder architecture, each pixel is classified as being inside an internal texture region or in a border between two different textures. The network is trained using the Prague Texture Segmentation Datagenerator and Benchmark and tested using the same dataset, besides the Brodatz textures dataset, and the Describable Texture Dataset. The method is also evaluated on the separation of regions in images from different applications, namely remote sensing images and H&E-stained tissue images. It is shown that the method has a good performance on different test sets, can precisely identify borders between texture regions and does not suffer from over-segmentation.

Automatic gauze tracking in laparoscopic surgery using image texture analysis

BACKGROUND AND OBJECTIVE

Inadvertent retained surgical gauzes are an infrequent medical error but can have devastating consequences in the patient health and in the surgeon professional reputation. This problem seems easily preventable implementing standardized protocols for counting but due to human errors it still persists in surgery. The omnipresence of gauzes, their small size, and their similar appearance with tissues when they are soaked in blood make this error eradication really complex. In order to reduce the risk of accidental retention of surgical sponges in laparoscopy operations, in this paper we present an image processing system that tracks the gauzes on the video captured by the endoscope.

METHODS

The proposed image processing application detects the presence of gauzes in the video images using texture analysis techniques. The process starts dividing the video frames into square blocks and each of these blocks is analyzed to determine whether it is similar to the gauze pattern. The video processing algorithm has been tested in a laparoscopic simulator under different conditions: with clean, slightly stained and soaked in blood gauzes as well as against different biological background tissues. Several methods, including different Local Binary Patterns (LBP) techniques and a convolutional neural network (CNN), have been analyzed in order to achieve a reliable detection in real time.

RESULTS

The proposed LBP algorithm classifies the individual blocks in the image with 98% precision and 94% sensitivity which is sufficient to make a robust detection of any gauze that appears in the endoscopic video even if it is stained or soaked in blood. The results provided by the CNN are superior with 100% precision and 97% sensitivity, but due to the high computational demand, real-time video processing is not attainable in this case with standard hardware.

CONCLUSIONS

The algorithm presented in this paper is a valuable tool to avoid the retention of surgical gauzes not only because of its reliability but also because it processes the video transparently and unattended, without the need for additional manipulation of special equipment in the operating room.