Image formalization space: Formulation of tasks, structural properties, and elements

Recently, pre-trained deep convolutional neural networks (DCNNs or ConvNets) have proven that the high-level features extracted at the top fully connected (FC) layer can improve the accuracy of various image understanding, recognition, and classification tasks. However, it has not been explored if such high-level features from different DCNN architectures contain complementary cues for image representation. Thence, in this paper, we further investigate a feature embedding strategy to exploit high-level features from multiple DCNNs in a framework of image-based object/action classification. We derive a generalized feature space by embedding different high-level features extracted through three ConvNets under Principal component analysis (PCA)-based reconstruction, energy level-based normalization, and five different fusion rules. Test outcomes on four different object classification datasets and an action classification dataset show that regardless of variation in image statistics and tasks the proposed multi-DCNN high-level feature embedding is well suited for the aforesaid tasks and it can be an effective complement of DCNN. In general, we observe that the proposed strategy is highly competitive with other approaches and tends to produce improvement in the classification accuracy.

Deep Learning in Medical Ultrasound Analysis: A Review

An approach to integrating the global and local kernel-based automated analysis of vocal fold images aiming to categorize laryngeal diseases is presented in this paper. The problem is treated as an image analysis and recognition task. A committee of support vector machines is employed for performing the categorization of vocal fold images into healthy, diffuse and nodular classes. Analysis of image color distribution, Gabor filtering, cooccurrence matrices, analysis of color edges, image segmentation into homogeneous regions from the image color, texture and geometry view point, analysis of the soft membership of the regions in the decision classes, the kernel principal components based feature extraction are the techniques employed for the global and local analysis of laryngeal images. Bearing in mind the high similarity of the decision classes, the correct classification rate of over 94% obtained when testing the system on 785 vocal fold images is rather encouraging.

Visual information, in the form of images and video, comes from the interaction of light with objects. Illumination is a fundamental element of visual information. Detecting and interpreting illumination effects is part of our everyday life visual experience. Shading for instance allows us to perceive the three-dimensional nature of objects. Shadows are particularly salient cues for inferring depth information. However, we do not make any conscious or unconscious effort to avoid them as if they were an obstacle when we walk around. Moreover, when humans are asked to describe a picture, they generally omit the presence of illumination effects, such as shadows, shading, and highlights, to give a list of objects and their relative position in the scene. Processing visual information in a way that is close to what the human visual system does, thus being aware of illumination effects, represents a challenging task for computer vision systems. Illumination phenomena interfere in fact with fundamental tasks in image analysis and interpretation applications, such as object extraction and description. On the other hand, illumination conditions are an important element to be considered when creating new and richer visual content that combines objects from different sources, both natural and synthetic. When taken into account, illumination effects can play an important role in achieving realism. Among illumination effects, shadows are often integral part of natural scenes and one of the elements contributing to naturalness of synthetic scenes. In this thesis, the problem of extracting shadows from digital images is discussed. A new analysis method for the segmentation of cast shadows in still and moving images without the need of human supervision is proposed. The problem of separating moving cast shadows from moving objects in image sequences is particularly relevant for an always wider range of applications, ranging from video analysis to video coding, and from video manipulation to interactive environments. Therefore, particular attention has been dedicated to the segmentation of shadows in video. The validity of the proposed approach is however also demonstrated through its application to the detection of cast shadows in still color images. Shadows are a difficult phenomenon to model. Their appearance changes with changes in the appearance of the surface they are cast upon. It is therefore important to exploit multiple constraints derived from the analysis of the spectral, geometric and temporal properties of shadows to develop effective techniques for their extraction. The proposed method combines an analysis of color information and of photometric invariant features to a spatio-temporal verification process. With regards to the use of color information for shadow analysis, a complete picture of the existing solutions is provided, which points out the fundamental assumptions, the adopted color models and the link with research problems such as computational color constancy and color invariance. The proposed spatial verification does not make any assumption about scene geometry nor about object shape. The temporal analysis is based on a novel shadow tracking technique. On the basis of the tracking results, a temporal reliability estimation of shadows is proposed which allows to discard shadows which do not present time coherence. The proposed approach is general and can be applied to a wide class of applications and input data. The proposed cast shadow segmentation method has been evaluated on a number of different video data representing indoor and outdoor real-world environments. The obtained results have confirmed the validity of the approach, in particular its ability to deal with different types of content and its robustness to different physically important independent variables, and have demonstrated the improvement with respect to the state of the art. Examples of application of the proposed shadow segmentation tool to the enhancement of video object segmentation, tracking and description operations, and to video composition, have demonstrated the advantages of a shadow-aware video processing.

Review on self-supervised image recognition using deep neural networks

This study investigates the computing capabilities and potential applications of neural oscillators to grey scale and colour image segmentation, an important task in image understanding and object recognition. A proposed neural system that combines the synergy between neural oscillators and Kohonen self-organising maps (SOM) is presented. Colour image segmentation is achieved through temporal synchronisation of neural oscillators that are mapped to pixels of the same object. Neurons are organised in a two-dimensional grid and are locally connected through excitatory connections and globally connected to a common inhibitor. Self-organising maps form the basis of a colour reduction system whose output is fed to a 2D grid of neural oscillators such as each neuron is mapped to a pixel of the input image. Both chromatic and local spatial features are used. The proposed system is simulated in Matlab and its demonstration on real world colour images shows promising results and the emergence of a new bio-inspired approach for colour image segmentation.

Deep learning has a strong ability to tackle pixel- level labeling tasks in image understanding. However, the disorder and irregularity of 3D point cloud data make it difficult to be applied. Though there are a few approaches that have acquired satisfied results on 3D data processing recently, there is no consideration of the relationships between each point, which plays an important role in indoor objects semantic segmentation and has been proved on plane images. In this paper, a spatial long-term connection of points is modeled by a fully connected conditional random field (CRF) to enhance the memory ability of the network. Since it is infeasible to compute due to the dimension explosion caused by potentially fully connected CRF, a highly efficient method in utilizing linear combination of multiple Gaussian kernels is proposed to approximate it. Finally, the CRF has been integrated into the deep learning framework, making it trainable end-to-end. The test evaluation of the experiments show that this network reaches current benchmarks and have a strong performance on public 3D indoor datasets. From these results, it is concluded that the relationships of each pair of points are conductive to semantic segmentation for indoor scenes.

Deep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications.

Intelligent colour analysis based on deep learning has a wide range of applications in image, video, and other colour information automatic analysis and understanding and has great potential. Deep learning models can learn the representation of color features through the process of feature abstraction and hierarchical extraction and feature learning to express colors, as well as pattern recognition that is suitable for the given task. They have stronger feature representation, learning, and generalization abilities. These characteristics allow deep learning models to better deal with the problems incurred by traditional methods in the processing, analysis, and understanding of colour and its features. The author mainly uses Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to analyse and process color data through the designed experimental system, respectively. The learning process of deep learning model is fully automatic, and the representation and abstraction ability of the model is improved through the large-scale annotated data. It can be used in the field of image/video recognition and understanding of color by deep learning method. The experimental results are shown in this paper. The application of deep learning-based color intelligent analysis in different tasks has achieved remarkable results. A deep learning model can accurately analyse the color and color texture of the image and its distribution in the image, and be used in the image recognition and classification task.

ABSTACT Image segmentation has been an important and challenging issue in the field of computer vision over decades. It plays a critical role for most image analysis tasks, such as object detection and recognition. The aim of this paper is to obtain segmented image of Printed Circuit Board (PCB)’s track using mathematical morphological operation. Morphological image analysis is based on the idea that images represent a collection of spatial patterns that can be analyzed based on some predefined patterns called structuring elements. Most basic morphological operation, dilation and erosion have been employed in this research. Detail elaboration on this method will be discussed and experimental results are presented.

The GRAFIX I system was developed in the late 1960's as a fast flexible system for processing and analyzing filmed images, particularly of material which is essentially binary (black and white), such as printed text, line drawings, certain biomedical images, fingerprints, etc. It incorporates a large scale general purpose time shared computer to provide the facilities for the efficient development of algorithms necessary to perform various image processing and analysis tasks. In addition it contains a fast, high resolution flying-spot film scanner and a powerful and rather general slave processor (the binary image processor, or BIP) which provide data collection and manipulation facilities adequate to perform image processing and analysis tasks at commercially practical speeds. So far it has been successfully employed in a commercial environment to the reading of printed multifont text in complex page formats, and to the reading of Cyrillic, Greek and even handprinted text. At present we are considering future applications beyond the area of optical character recognition, particularly the analysis of engineering drawings, as well as the automatic analysis and classification of fingerprints, the analysis of biomedical images such as chromosomes, the analysis of x-ray images, and the analysis of satellite imagery data, among others.

Extraction of linear features is an important task in many image understanding and computer vision systems. In this paper, we describe a linear feature extracor which operates on the edge pixels detected by a space varying 2 - D autoregressive (AR) model. The sequence of steps for extraction of linear segments consists of tracing the edge points, linking and fitting with lines. The heuristics used in tracing and linking steps are specific to the characteristics of the AR model based edge detector. The performance of the linear feature extractor is illustrated using real images.

Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases

This research aims to study the deep learning applications in image recognition and classification tasks. The advantages and limitations of deep learning are explored by analysing existing deep learning algorithms and their applications on tasks such as using images to do classification, image segmentation, and target detection. In the experimental part, this paper evaluates the performance of deep learning in image recognition by using classical neural network models, including training and testing models on a large size of image datasets. The results show that neural network has good classification and detection capabilities in image recognition tasks and also achieves good results for image segmentation tasks. However, the model training process of shallow neural network models is time-consuming and performs poorly for small-scale datasets. Based on these situations, this paper proposes some optimization strategies to achieve high performance and efficiency of neural networks in image recognition and analyze the performance differences between different strategies .

Multioutput regression has recently shown great ability to solve challenging problems in both computer vision and medical image analysis. However, due to the huge image variability and ambiguity, it is fundamentally challenging to handle the highly complex input-target relationship of multioutput regression, especially with indiscriminate high-dimensional representations. In this paper, we propose a novel supervised descriptor learning (SDL) algorithm for multioutput regression, which can establish discriminative and compact feature representations to improve the multivariate estimation performance. The SDL is formulated as generalized low-rank approximations of matrices with a supervised manifold regularization. The SDL is able to simultaneously extract discriminative features closely related to multivariate targets and remove irrelevant and redundant information by transforming raw features into a new low-dimensional space aligned to targets. The achieved discriminative while compact descriptor largely reduces the variability and ambiguity for multioutput regression, which enables more accurate and efficient multivariate estimation. We conduct extensive evaluation of the proposed SDL on both synthetic data and real-world multioutput regression tasks for both computer vision and medical image analysis. Experimental results have shown that the proposed SDL can achieve high multivariate estimation accuracy on all tasks and largely outperforms the algorithms in the state of the arts. Our method establishes a novel SDL framework for multioutput regression, which can be widely used to boost the performance in different applications.