MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of a set of “basis filters.” Steerable properties dominate the design of the traditional filters, e.g., Gabor filters and endow features the capability of handling spatial transformations. However, such properties have not yet been well explored in the deep convolutional neural networks (DCNNs). In this paper, we develop a new deep model, namely, Gabor convolutional networks (GCNs or Gabor CNNs), with Gabor filters incorporated into DCNNs such that the robustness of learned features against the orientation and scale changes can be reinforced. By manipulating the basic element of DCNNs, i.e., the convolution operator, based on Gabor filters, GCNs can be easily implemented and are readily compatible with any popular deep learning architecture. We carry out extensive experiments to demonstrate the promising performance of our GCNs framework, and the results show its superiority in recognizing objects, especially when the scale and rotation changes take place frequently. Moreover, the proposed GCNs have much fewer network parameters to be learned and can effectively reduce the training complexity of the network, leading to a more compact deep learning model while still maintaining a high feature representation capacity. The source code can be found at https://github.com/bczhangbczhang .

/pdf/gabor-convolutional-networks-3rx97w8vhd.pdf

Gabor Convolutional Networks

Steerable properties dominate the design of traditional filters, e.g., Gabor filters, and endow features the capability of dealing with spatial transformations. However, such excellent properties have not been well explored in the popular deep convolutional neural networks (DCNNs). In this paper, we propose a new deep model, termed Gabor Convolutional Networks (GCNs or Gabor CNNs), which incorporates Gabor filters into DCNNs to enhance the resistance of deep learned features to the orientation and scale changes. By only manipulating the basic element of DCNNs based on Gabor filters, i.e., the convolution operator, GCNs can be easily implemented and are compatible with any popular deep learning architecture. Experimental results demonstrate the super capability of our algorithm in recognizing objects, where the scale and rotation changes occur frequently. The proposed GCNs have much fewer learnable network parameters, and thus is easier to train with an end-to-end pipeline.

/pdf/gabor-convolutional-networks-1uto0gsgk2.pdf

Image Enhancement is a crucial phase in almost every image processing system It aims at improving both the visual and the informational quality of distorted images Histogram Equalization (HE) techniques are the most popular approaches for image enhancement for they succeed in enhancing the image and preserving its main characteristics However, using exhaustive approaches for histogram equalisation is an algorithmically complex task These HE techniques also fail in offering good enhancement if not so good parameters are chosen So, new intelligent approaches, using Artificial Intelligence techniques, have been proposed for image enhancement In this context, this paper proposes a new Artificial Bee Colony (ABC) algorithm for image contrast enhancement A grey-level mapping technique and a new image quality measure are used The algorithm has been tested on some test images, and the comparisons of the obtained results with the genetic algorithm have proven its superiority Moreover, the proposed algorithm has been extended to colour image enhancement and given very promising results Further qualitative and statistical comparisons of the proposed ABC to the Cuckoo Search (CS) algorithm are also presented in the paper; not only for the adopted grey-level mapping technique, but also with using another common transformation, generally called the local/global transformation

An artificial bee colony algorithm for image contrast enhancement

The continuous improvements in the area of medical imaging, makes the patient monitoring a crucial concern. The internet of things (IoT) embedded in a medical technologies to collect data from human body through sensors, wireless connectivity etc. The junction of medicine and IT like medical informatics will transform healthcare, curbing cost, make more efficient, and saving lives. Various computerized techniques are implemented in the area of Artificial Intelligence (AI) for the application of medical imaging to diagnose the infected regions in the images and videos such as WCE and pathology. The famous stomach infections are ulcer, polyp, and bleeding. Stomach cancer is the most common infection and a leading cause of human deaths worldwide. In the USA, since 2019, a total of 27,510 new cases are reported including 17,230 men and 10,230 women. While the number of deaths is 11,140 consists of 6,800 men and 4,340 women. The manual diagnosis of these stomach infections is a difficult and agitated process therefore it is required to design a fully automated system using AI. In this article, we presented a fully automated system for stomach infection recognition based on deep learning features fusion and selection. In this design, ulcer images are assigned manually and support to a saliency-based method for ulcer detection. Later, pre-trained deep learning model named VGG16 is employing and re-trained using transfer learning. Features of re-trained model are extracted from two consecutive fully connected layers and fused by array-based approach. Besides, the best individuals are selected through the metaheuristic approach name PSO along mean value-based fitness function. The selected individuals are finally recognized through Cubic SVM. The experiments are conducted on Private collected dataset and achieved an accuracy of 98.4%, which is best as compared to existing state-of-the-art techniques.

/pdf/computer-aided-gastrointestinal-diseases-analysis-from-5fqu69e3xp.pdf

Computer-Aided Gastrointestinal Diseases Analysis From Wireless Capsule Endoscopy: A Framework of Best Features Selection

Feature extraction and classification are two important components in object recognition. While the traditional methods design these components individually, the deep neural networks jointly learn these two parts. In this paper, we propose a method of the convolutional neural network combined with Gabor filters for strengthening the learning of texture information. We called this model as Gabor-CNN below. Through experiments, the approach achieves the recognition rate of 81.53%, yielding a 1.26% promotion in the average accuracy rate compared with the results obtained using the convolutional neural network model alone on the ImageNet10 dataset, as well as significantly outperforming the traditional method based on Bag-of-Words model with SIFT.

Gabor Feature Based Convolutional Neural Network for Object Recognition in Natural Scene

Image segmentation is still a crucial problem in image processing It hasn yet been solved very well In this study, we propose a novel multi-level thresholding image segmentation method based on PSNR using artificial bee colony algorithm (ABCA) PSNR is considered as an objective function of ABCA The multi-level thresholds (t*1, t*2 ,, t*n-1, t*n) are those maximizing the PSNR We compare entropy and PSNR in segmenting gray-level images The experiments results demonstrate proposed method is effective and efficient

Multi-level Threshold Image Segmentation Based on PSNR using Artificial Bee Colony Algorithm

/pdf/k-means-multi-threshold-image-segmentation-based-on-firefly-3mjj1zg1nq.pdf

K - means multi-threshold image segmentation based on firefly algorithm

Image segmentation is still a crucial problem in image processing In this paper, we proposed a novel multi-level image segmentation method based on PSNR using artificial bee colony algorithm (ABCA) PSNR is considered as an objective function of ABCA The best multi-level thresholds are those which can make the PSNR maximize Further, we compare entropy and PSNR in segmenting gray-level images and noisy images Through experiments, it is found that the entropy isn't suitable to be applied to segmentation of images with Gaussian noise So we can conclude that entropy can't be used for noisy image segmentation The experiments results demonstrate our proposed method is effective and efficient

Multi-level Threshold Image Segmentation Using Artificial Bee Colony Algorithm

The job shop scheduling problem (JSSP) is a model of production scheduling. The goal is to solve the problem how to use the limited resources to schedule the order and time of the workpiece and equipment to meet the various production constraints with multiple performances. In this paper, the artificial bee colony algorithm combined with the genetic algorithm, solve the JSSP. The proposed method overcome their shortcomings and realize the complementary advantages and get a more efficient workshop scheduling plan.

Yu Weiyu

Papers

Gabor Feature Based Convolutional Neural Network for Object Recognition in Natural Scene

Multi-level Threshold Image Segmentation Based on PSNR using Artificial Bee Colony Algorithm

K - means multi-threshold image segmentation based on firefly algorithm

Multi-level Threshold Image Segmentation Using Artificial Bee Colony Algorithm

Artificial bee colony algorithm with genetic algorithm for job shop scheduling problem