Problem Of Object Recognition Research Articles

Enhanced Convolution Neural Network for Tomato Leaf Disease Classification

When plants and crops are affected by pests it affects the agricultural production of the country. Agricultural productivity depends heavily on the economy. This is one of the reasons why plant disease detection plays a major role in agriculture. Usually farmers or experts observe the plants with naked eye for detection and identification of disease. But this method can be time processing, expensive and inaccurate. Detection of crop disease using a few instantaneous strategy is helpful as it decreases comprehensive surveillance job in huge crop farms and locates disease side effects quite soon, i.e. if they tend on leaves and stems. Enhanced Convolutional neural networks (ECNN) have demonstrated great performance in object recognition and image classification problems. Using a public dataset images of infected and healthy Tomato leaves collected under controlled conditions, we trained a deep convolutional neural network to identify diseases in tomato. As the result, few diseases that usually occur in tomato plants such as Late blight, Gray spot and bacterial canker are detected.

Human Depth Sensitivity Is Affected by Object Plausibility.

Using behavioral and fMRI paradigms, we asked how the physical plausibility of complex 3-D objects, as defined by the object's congruence with 3-D Euclidean geometry, affects behavioral thresholds and neural responses to depth information. Stimuli were disparity-defined geometric objects rendered as random dot stereograms, presented in plausible and implausible variations. In the behavior experiment, observers were asked to complete (1) a noise-based depth task that involved judging the depth position of a target embedded in noise and (2) a fine depth judgment task that involved discriminating the nearer of two consecutively presented targets. Interestingly, results indicated greater behavioral sensitivities of depth judgments for implausible versus plausible objects across both tasks. In the fMRI experiment, we measured fMRI responses concurrently with behavioral depth responses. Although univariate responses for depth judgments were largely similar across cortex regardless of object plausibility, multivariate representations for plausible and implausible objects were notably distinguishable along depth-relevant intermediate regions V3 and V3A, in addition to object-relevant LOC. Our data indicate significant modulations of both behavioral judgments of and neural responses to depth by object context. We conjecture that disparity mechanisms interact dynamically with the object recognition problem in the visual system such that disparity computations are adjusted based on object familiarity.

COMPRESSIVE SENSING BASED CONVOLUTIONAL NEURAL NETWORK FOR OBJECT DETECTION

Deep neural networks (DNN) have shown significant performance in several domains including computer vision and machine learning. Convolutional Neural Networks (CNN), known as a particular type of DNN, have shown their promising potentials in discovering vision-based patterns from quantity of labeled images. Many CNN-based algorithms are thus proposed to solve the problem of object detection and object recognition. However, CNN-based systems are hard to deploy on embedded systems due to their computationally and storage intensive. In this paper, we propose a method to compress convolutional neural network to decreases its computation and storage cost by exploiting inherent redundancy property of parameters in different kinds of layers of CNN architecture. During the compression, we firstly construct parameter matrices from different kinds of layers and convert parameter matrices to frequency domain through discrete cosine transform (DCT). Due to the smooth property of parameters when processing images, the resulting frequency matrices are dominated by low-frequency components. We thus prune high-frequency part to emphasize the dominating part of frequency matrix and make the frequency matrix sparse. Then, the sparse frequency matrices are sampled with distributed random Gaussian matrix under the guiding of compress sensing. Finally, we retrain the network with the sampling matrices to fine-tune the remaining parameters. We evaluate the proposed method on several typical convolutional neural network and show it outperforms one latest compression approach.

Research and implementation of NN based on TensorFlow

TensorFlow is Google’s open-source machine learning and deep learning framework, which is convenient and flexible to build the current mainstream deep learning model. Convolutional neural network is a classical model of deep learning, the advantage lies in its powerful feature extraction capabilities of convolutional blocks. A neural network in the simplest case is a mathematical model consisting of several layers of elements that perform parallel calculations. Initially, such an architecture was created by analogy with the small computing elements of the human brain — neurons. The minimal computing elements of an artificial neural network are also called neurons. Neural networks typically consist of three or more layers: an input layer, a hidden layer (or layers), and an output layer. An important feature of the neural network is its ability to learn by example, this is called learning with a teacher. The neural network is trained on a large number of examples consisting of input-output pairs (corresponding to each other input and output). In object recognition problems, such a pair will be the input image and the corresponding label — the name of the object. Neural network learning is an iterative process that reduces the deviation of the network output from a given «teacher response» — a label that corresponds to a given image. This process consists of steps called epochs of learning (they are usually calculated in thousands), each of which is the adjustment of the «weights» of the neural network — the parameters of the hidden layers of the network. Upon completion of the learning process, the quality of the neural network is usually good enough to perform the task for which it was trained, although the optimal set of parameters that perfectly recognizes all the images, it is often impossible to choose. Based on the TensorFlow platform, a convolutional neural network model with two-convolution-layers was built. The model was trained and tested with the MNIST data set. The test accuracy rate could reach 99,15%, and compared with the rate of 98,69% with only one-convolution-layer model, which shows that the two-convolution-layers convolutional neural network model has a better ability of feature extraction and classification decision-making.

X-Ray Baggage Inspection With Computer Vision: A Survey

In the last decades, baggage inspection based on X-ray imaging has been established to protect environments in which access control is of vital significance. In several public entrances, like airports, government buildings, stadiums and large event venues, security checks are carried out on all baggage to detect suspicious objects (e.g., handguns and explosives). Although improvements in X-ray technology and computer vision have made many X-ray detection tasks that were previously unfeasible a reality, the progress that has been made in automated baggage inspection is very limited compared to what is needed. For this reason, X-ray screening systems are usually being manipulated by human inspectors. Research and development experts who focus on X-ray testing are moving towards new approaches that can be used to aid human operators. This paper reports the state of the art in baggage inspection identifying three research fields that have been used to deal with this problem: i) X-ray energies, because there is enough research evidence to show that multi-energy X-ray testing must be used when the material characterization is required; ii) X-ray multi-views, because they can be an effective option for examining complex objects where the uncertainty of only one view can lead to misinterpretation; and iii) X-ray computer vision algorithms, because there are a plethora of computer vision approaches that can address many 3D object recognition problems. Besides, this paper presents useful public datasets that can be used for training and testing, and also summarizes the reported experimental results in this field. Finally, this paper addresses the general limitations and show new avenues for future research.

A neural network using a scalar product and defining several solutions

The Hamming neural network is a very effective tool for solving discrete object recognition problems, the binary components of which are described using bipolar components, and the difference between the number of identical bipolar components of the vectors and the Hamming distance between them is used as a proximity measure. For a finer classification of binary objects (vectors), a number of Hamming distance extensions are used, using various affinity functions (proximity or interconnection) between binary objects. The article proposes modifications of the Hamming neural network, in which instead of the Hamming distance, other affinity functions between binary vectors are proposed. Figs.: 7. Tabl.: 2. Refs.: 8 titles. Keywords: neural network; Hamming distance; affinity functions between binary vectors; discrete objects.

Key Algorithms of Video Target Detection and Recognition in Intelligent Transportation Systems

With the popularization of video detection and recognition systems and the advancement of video image processing technology, the application research of intelligent transportation systems based on computer vision technology has received more and more attention. It comprehensively utilizes image processing, pattern recognition, artificial intelligence and other technologies. It also involves processing and analyzing the video image sequence collected by the detection system, intelligently understanding the video content and making processing, and dealing with various problems such as accident information judgment, pedestrian and vehicle classification, traffic flow parameter detection, and moving target tracking. It promotes intelligent transportation systems to be more intelligent and practical, and provides comprehensive, real-time traffic status information for traffic management and control. Therefore, the research on the method of traffic information detection based on computer vision has important theoretical and practical significance. The detection and recognition of video targets is an important research direction in the field of intelligent transportation and computer vision. However, due to the background complexity, illumination changes, target occlusion and other factors in the detection and recognition environment, the application still faces many difficulties, and the robustness and accuracy of detection and recognition need to be further improved. In this paper, several key problems in video object detection and recognition are studied, including accurate segmentation of target and background, shadow in complex scenes; accurate classification of extracted foreground targets; and target recognition in complex background. In response to these problems, this paper proposes a corresponding solution.

Assistance via IoT networking cameras and evidence theory for 3D object instance recognition: Application for the NAO humanoid robot

Object recognition problem based on cameras has become one of the most important tasks in robotics. Nevertheless, for a robot equipped with a camera and evolving in uncontrolled environment, many factors can limit the quality of its recognition, such as lighting conditions, conflict situations, occlusion, and cameras orientations, etc. Under theses imperfections, a single robot camera can provide incomplete and unreliable information and is thus limited to deal with complex recognition situations, particularly in imprecise and uncertain environments. Under such circumstances, in this paper, an IoT (Internet of Things) multi-camera embedded 3D object recognition system, including a NAO humanoid robot and other IoT heterogeneous cameras (2D and 3D), is proposed. These cameras can be complementary, and their combination increases the recognition reliability of the single robot camera. The used IoT infrastructure allows the communication between the robot and different connected cameras using internet protocols. The proposed recognition system uses evidence theory to fuse the data issued from these IoT sources for making the recognition decision. This paper aims at demonstrating the advantages of coupling the IoT technology with the evidence theory concepts for improving the 3D object recognition for the NAO robot. Through the proposed application, our method has been validated and its performance has been compared with a deep learning approach.

Generation of classification schemes in the form of logical trees in discrete object recognition problems

This work is devoted to the problems of recognition of discrete objects. It continues a series of articles devoted to the study of recognition systems in the form of logical trees, optimization of synthesized systems of classification of discrete objects, studies of their maximum complexity and the possibility of building effective methods to minimize them. Here the scheme of construction of system of recognition of discrete objects on the basis of a logical tree is step by step considered, and in the center of research there is a graph-circuit model of system of recognition in the form of a logical tree. Note that the results of this robot are relevant for all pattern recognition problems, in which the resulting recognition scheme can be represented as a logical tree.

Progressive Operational Perceptrons with Memory

Generalized Operational Perceptron (GOP) was proposed to generalize the linear neuron model used in the traditional Multilayer Perceptron (MLP) by mimicking the synaptic connections of biological neurons showing nonlinear neurochemical behaviours. Previously, Progressive Operational Perceptron (POP) was proposed to train a multilayer network of GOPs which is formed layer-wise in a progressive manner. While achieving superior learning performance over other types of networks, POP has a high computational complexity. In this work, we propose POPfast, an improved variant of POP that signicantly reduces the computational complexity of POP, thus accelerating the training time of GOP networks. In addition, we also propose major architectural modications of POPfast that can augment the progressive learning process of POP by incorporating an information preserving, linear projection path from the input to the output layer at each progressive step. The proposed extensions can be interpreted as a mechanism that provides direct information extracted from the previously learned layers to the network, hence the term “memory”. This allows the network to learn deeper architectures and better data representations. An extensive set of experiments in human action, object, facial identity and scene recognition problems demonstrates that the proposed algorithms can train GOP networks much faster than POPs while achieving better performance compared to original POPs and other related algorithms.

Object Recognition in Image Sequence using Heuristic Convolution Neural Network

The human visual system can make a distinction of tiger from cat very easily without taking any efforts. But in case of a computer system, it is a very complicated job. Identifying and differentiating task has to deal with many challenges but the human brain makes it effortless. Self learning or heuristic techniques are most relevant in this area. The recognition task is to search for the particular object of same shape, color and texture and so on, of the trained objects and match with input. The geometrical distinction such as zoom in, zoom out, rotation etc result in poor performance. This paper uses convolution neural network models Alexnet and VGGNet on object recognition problems which are added with novel heuristic method. We have used CIFAR-10 dataset. The performance and computation speeds are found efficient.

3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey.

This paper addresses the problem of object recognition from colorless 3D point clouds in underwater environments. It presents a performance comparison of state-of-the-art global descriptors, which are readily available as open source code. The studied methods are intended to assist Autonomous Underwater Vehicles (AUVs) in performing autonomous interventions in underwater Inspection, Maintenance and Repair (IMR) applications. A set of test objects were chosen as being representative of IMR applications whose shape is typically known a priori. As such, CAD models were used to create virtual views of the objects under realistic conditions of added noise and varying resolution. Extensive experiments were conducted from both virtual scans and from real data collected with an AUV equipped with a fast laser sensor developed in our research centre. The underwater testing was conducted from a moving platform, which can create deformations in the perceived shape of the objects. These effects are considerably more difficult to correct than in above-water counterparts, and therefore may affect the performance of the descriptor. Among other conclusions, the testing we conducted illustrated the importance of matching the resolution of the database scans and test scans, as this significantly impacted the performance of all descriptors except one. This paper contributes to the state-of-the-art as being the first work on the comparison and performance evaluation of methods for underwater object recognition. It is also the first effort using comparison of methods for data acquired with a free floating underwater platform.

Transfer Learning with Convolutional Neural Networks for IRIS Recognition

Iris is one of the common biometrics used for identity authentication. It has the potential to recognize persons with a high degree of assurance. Extracting effective features is the most important stage in the iris recognition system. Different features have been used to perform iris recognition system. A lot of them are based on hand-crafted features designed by biometrics experts. According to the achievement of deep learning in object recognition problems, the features learned by the Convolutional Neural Network (CNN) have gained great attention to be used in the iris recognition system. In this paper, we proposed an effective iris recognition system by using transfer learning with Convolutional Neural Networks. The proposed system is implemented by fine-tuning a pre-trained convolutional neural network (VGG-16) for features extracting and classification. The performance of the iris recognition system is tested on four public databases IITD, iris databases CASIA-Iris-V1, CASIA-Iris-thousand and, CASIA-Iris-Interval. The results show that the proposed system is achieved a very high accuracy rate.

A Transfer Learning Approach to Cross-Modal Object Recognition: From Visual Observation to Robotic Haptic Exploration

In this work, we introduce the problem of cross-modal visuo-tactile object recognition with robotic active exploration. With this term, we mean that the robot observes a set of objects with visual perception and, later on, it is able to recognize such objects only with tactile exploration, without having touched any object before. Using a machine learning terminology, in our application we have a visual training set and a tactile test set, or vice versa. To tackle this problem, we propose an approach constituted by four steps: finding a visuo-tactile common representation, defining a suitable set of features, transferring the features across the domains, and classifying the objects. We show the results of our approach using a set of 15 objects, collecting 40 visual examples and five tactile examples for each object. The proposed approach achieves an accuracy of 94.7%, which is comparable with the accuracy of the monomodal case, i.e., when using visual data both as training set and test set. Moreover, it performs well compared to the human ability, which we have roughly estimated carrying out an experiment with ten participants.

Deep0Tag: Deep Multiple Instance Learning for Zero-Shot Image Tagging

Zero-shot learning aims to perform visual reasoning about unseen objects. In-line with the success of deep learning on object recognition problems, several end-to-end deep models for zero-shot recognition have been proposed in the literature. These models are successful in predicting a single unseen label given an input image but do not scale to cases where multiple unseen objects are present. Here, we focus on the challenging problem of zero-shot image tagging, where multiple labels are assigned to an image, that may relate to objects, attributes, actions, events, and scene type. Discovery of these scene concepts requires the ability to process multi-scale information. To encompass global as well as local image details, we propose an automatic approach to locate relevant image patches and model image tagging within the Multiple Instance Learning (MIL) framework. To the best of our knowledge, we propose the first end-to-end trainable deep MIL framework for the multi-label zero-shot tagging problem. We explore several alternatives for instance-level evidence aggregation and perform an extensive ablation study to identify the optimal pooling strategy. Due to its novel design, the proposed framework has several interesting features: 1) unlike previous deep MIL models, it does not use any off-line procedure (e.g., Selective Search or EdgeBoxes) for bag generation. 2) During test time, it can process any number of unseen labels given their semantic embedding vectors. 3) Using only image-level seen labels as weak annotation, it can produce a localized bounding box for each predicted label. We experiment with the large-scale NUS-WIDE and MS-COCO datasets and achieve superior performance across conventional, zero-shot, and generalized zero-shot tagging tasks.

Multi-Scale Gradient Image Super-Resolution for Preserving SIFT Key Points in Low-Resolution Images

Low-resolution images present challenges to a variety of object recognition problems in a variety of surveillance and navigation applications. In recent years, deep learning has advanced the state of the art in image super-resolution (SR) in terms of pixel domain peak signal to noise ratio (PSNR)/ mean square error (MSE). Inspired by the recent advances of deep convolutional neural networks in general image SR tasks, we develop a computer vision task-driven image SR solution by learning super-resolved gradient images using multiple convolutional neural networks for different scales. Recovering super-resolved gradient images at multiple scales, enables the system to recover more information useful for high level vision tasks than simply SR in the pixel domain. In particular, we propose a residual learning framework to perform image SR in the Difference of Gaussian (DOG) domain. The trained residual network models are then adapted to drive a widely adopted key point algorithm for image recognition, i.e. the SIFT detection and matching. Experimental results show that the proposed approach can significantly improve the SIFT keypoints repeatability compared to the state of the art in pixel domain image SR solutions.

Application of neural networks in object recognition tasks for ADAS systems

Modern driver assistance systems (ADAS) require an environmental recognition function to inform the driver and for making management decisions. Neural networks are used to select and recognize objects in such systems. The paper presents the results of comparative analysis of various neural networks in object recognition problems. Experimental data showed that convolutional neural networks show the best results in recognition problems.

Energy Efficiency Enhancement for CNN-based Deep Mobile Sensing

Recently, deep learning has been used to tackle mobile sensing problems, and the inference phase of deep learning is preferred to be run on mobile devices for speedy responses. However, mobile devices are resource-constrained platforms for both computation and power. Moreover, an inference task with deep learning involves tens of billions of mathematical operations and tens of millions of parameter reads. Thus, it is a critical issue to reduce the energy consumption of deep learning inference algorithms. In this article, we survey various energy reduction approaches, and classify them into three categories: the compressing neural network model, minimizing the data transfer required in computation, and offloading workloads. Moreover, we simulate and compare three techniques of model compression, by applying them to an object recognition problem.

Granulated deep learning and Z-numbers in motion detection and object recognition

The article deals with the problems of motion detection, object recognition, and scene description using deep learning in the framework of granular computing and Z-numbers. Since deep learning is computationally intensive, whereas granular computing, on the other hand, leads to computation gain, a judicious integration of their merits is made so as to make the learning mechanism computationally efficient. Further, it is shown how the concept of z-numbers can be used to quantify the abstraction of semantic information in interpreting a scene, where subjectivity is of major concern, through recognition of its constituting objects. The system, thus developed, involves recognition of both static objects in the background and moving objects in foreground separately. Rough set theoretic granular computing is adopted where rough lower and upper approximations are used in defining object and background models. During deep learning, instead of scanning the entire image pixel by pixel in the convolution layer, we scan only the representative pixel of each granule. This results in a significant gain in computation time. Arbitrary-shaped and sized granules, as expected, perform better than regular-shaped rectangular granules or fixed-sized granules. The method of tracking is able to deal efficiently with various challenging cases, e.g., tracking partially overlapped objects and suddenly appeared objects. Overall, the granulated system shows a balanced trade-off between speed and accuracy as compared to pixel level learning in tracking and recognition. The concept of using Z-numbers, in providing a granulated linguistic description of a scene, is unique. This gives a more natural interpretation of object recognition in terms of certainty toward scene understanding.

A Novel Weakly-Supervised Approach for RGB-D-Based Nuclear Waste Object Detection

This paper addresses the problem of RGBD object recognition in real-world applications, where large amounts of annotated training data are typically unavailable. To overcome this problem, we propose a novel, weakly-supervised learning architecture (DCNN-GPC) which combines parametric models (a pair of Deep Convolutional Neural Networks (DCNN) for RGB and D modalities) with non-parametric models (Gaussian Process Classification). Our system is initially trained using a small amount of labeled data, and then automatically prop- agates labels to large-scale unlabeled data. We first run 3D- based objectness detection on RGBD videos to acquire many unlabeled object proposals, and then employ DCNN-GPC to label them. As a result, our multi-modal DCNN can be trained end-to-end using only a small amount of human annotation. Finally, our 3D-based objectness detection and multi-modal DCNN are integrated into a real-time detection and recognition pipeline. In our approach, bounding-box annotations are not required and boundary-aware detection is achieved. We also propose a novel way to pretrain a DCNN for the depth modality, by training on virtual depth images projected from CAD models. We pretrain our multi-modal DCNN on public 3D datasets, achieving performance comparable to state-of-the-art methods on Washington RGBS Dataset. We then finetune the network by further training on a small amount of annotated data from our novel dataset of industrial objects (nuclear waste simulants). Our weakly supervised approach has demonstrated to be highly effective in solving a novel RGBD object recognition application which lacks of human annotations.