Variety Of Image Datasets Research Articles

An Analysis Of Convolutional Neural Networks For Image Classification

This paper presents an empirical analysis of theperformance of popular convolutional neural networks (CNNs) for identifying objects in real time video feeds. The most popular convolution neural networks for object detection and object category classification from images are Alex Nets, GoogLeNet, and ResNet50. A variety of image data sets are available to test the performance of different types of CNN’s. The commonly found benchmark datasets for evaluating the performance of a convolutional neural network are anImageNet dataset, and CIFAR10, CIFAR100, and MNIST image data sets. This study focuses on analyzing the performance of three popular networks: Alex Net, GoogLeNet, and ResNet50. We have taken three most popular data sets ImageNet, CIFAR10, and CIFAR100 for our study, since, testing the performance of a network on a single data set does not reveal its true capability and limitations. It must be noted that videos are not used as a training dataset, they are used as testing datasets. Our analysis shows that GoogLeNet and ResNet50 are able to recognize objects with better precision compared to Alex Net. Moreover, theperformance of trained CNN’s vary substantially across different categories of objects and we, therefore, will discuss the possible reasons for this.

Medical, Scene And Event Image Category Recognition Using Completed Local Ternary Patterns (CLTP)

Many of texture descriptors are proposed based on the Local Binary Pattern (LBP) and have been achieved remarkable texture classification accuracy such as Completed LBP (CLBP) and Completed Local Binary Count (CLBC). However, the LBP suffers from two weaknesses where: 1) it is sensitive to noise and; 2) it sometimes classify two or more different patterns falsely to the same class. To overcome the LBP weaknesses, we propose a new texture descriptor which is defined as Completed Local Ternary Pattern (CLTP). The CLTP was used for rotation invariant texture classification. It demonstrates superior texture classification accuracy as compared to CLBP and CLBC descriptors. This is because, the CLTP is more robust to noise and has a high discriminating property that achieves impressive classification accuracy rates. In this paper, two types of experiments are carried out. In the first experiment, different amount of additive Gaussian noise is added to the TC10 Outex texture data set to investigate and prove the robustness of the CLTP against the noise. For the second experiment, the performance of CLTP for image category recognition is studied and investigated. A variety of image datasets are used in the experiments such as scene data set (e.g., Oliva and Torralba datasets (OT8)), Event sport datasets, 2D HeLa medical images, and our new scene data set, defined as USM scene data set. The experimental results proved the superiority of the CLTP descriptor over the original LBP, and different new texture descriptors such as CLBP in the image category recognition, as well as the robustness against the noise. In 2D HeLa medical images, the proposed CLTP has achieved the highest state of the art classification rate reaching 95.62%.

M-AMST: an automatic 3D neuron tracing method based on mean shift and adapted minimum spanning tree

BackgroundUnderstanding the working mechanism of the brain is one of the grandest challenges for modern science. Toward this end, the BigNeuron project was launched to gather a worldwide community to establish a big data resource and a set of the state-of-the-art of single neuron reconstruction algorithms. Many groups contributed their own algorithms for the project, including our mean shift and minimum spanning tree (M-MST). Although M-MST is intuitive and easy to implement, the MST just considers spatial information of single neuron and ignores the shape information, which might lead to less precise connections between some neuron segments. In this paper, we propose an improved algorithm, namely M-AMST, in which a rotating sphere model based on coordinate transformation is used to improve the weight calculation method in M-MST.ResultsTwo experiments are designed to illustrate the effect of adapted minimum spanning tree algorithm and the adoptability of M-AMST in reconstructing variety of neuron image datasets respectively. In the experiment 1, taking the reconstruction of APP2 as reference, we produce the four difference scores (entire structure average (ESA), different structure average (DSA), percentage of different structure (PDS) and max distance of neurons’ nodes (MDNN)) by comparing the neuron reconstruction of the APP2 and the other 5 competing algorithm. The result shows that M-AMST gets lower difference scores than M-MST in ESA, PDS and MDNN. Meanwhile, M-AMST is better than N-MST in ESA and MDNN. It indicates that utilizing the adapted minimum spanning tree algorithm which took the shape information of neuron into account can achieve better neuron reconstructions. In the experiment 2, 7 neuron image datasets are reconstructed and the four difference scores are calculated by comparing the gold standard reconstruction and the reconstructions produced by 6 competing algorithms. Comparing the four difference scores of M-AMST and the other 5 algorithm, we can conclude that M-AMST is able to achieve the best difference score in 3 datasets and get the second-best difference score in the other 2 datasets.ConclusionsWe develop a pathway extraction method using a rotating sphere model based on coordinate transformation to improve the weight calculation approach in MST. The experimental results show that M-AMST utilizes the adapted minimum spanning tree algorithm which takes the shape information of neuron into account can achieve better neuron reconstructions. Moreover, M-AMST is able to get good neuron reconstruction in variety of image datasets.

Online Multiple Kernel Similarity Learning for Visual Search

Recent years have witnessed a number of studies on distance metric learning to improve visual similarity search in content-based image retrieval (CBIR). Despite their successes, most existing methods on distance metric learning are limited in two aspects. First, they usually assume the target proximity function follows the family of Mahalanobis distances, which limits their capacity of measuring similarity of complex patterns in real applications. Second, they often cannot effectively handle the similarity measure of multimodal data that may originate from multiple resources. To overcome these limitations, this paper investigates an online kernel similarity learning framework for learning kernel-based proximity functions which goes beyond the conventional linear distance metric learning approaches. Based on the framework, we propose a novel online multiple kernel similarity (OMKS) learning method which learns a flexible nonlinear proximity function with multiple kernels to improve visual similarity search in CBIR. We evaluate the proposed technique for CBIR on a variety of image data sets in which encouraging results show that OMKS outperforms the state-of-the-art techniques significantly.

Fast Similarity Search for Learned Metrics

We introduce a method that enables scalable similarity search for learned metrics. Given pairwise similarity and dissimilarity constraints between some examples, we learn a Mahalanobis distance function that captures the examples' underlying relationships well. To allow sublinear time similarity search under the learned metric, we show how to encode the learned metric parameterization into randomized locality-sensitive hash functions. We further formulate an indirect solution that enables metric learning and hashing for vector spaces whose high dimensionality makes it infeasible to learn an explicit transformation over the feature dimensions. We demonstrate the approach applied to a variety of image data sets, as well as a systems data set. The learned metrics improve accuracy relative to commonly used metric baselines, while our hashing construction enables efficient indexing with learned distances and very large databases.