This article introduces a new connected component labeling and analysis algorithm for foreground and background labeling that computes the adjacency tree. The computation of features (bounding boxes, first statistical moments, Euler number) is done on-the-fly. The transitive closure enables an efficient hole processing that can be filled while their features are merged with the surrounding connected component without the need to rescan the image. A comparison with existing algorithms shows that this new algorithm can do all these computations faster than algorithms processing black and white components.
This report presents the results of a sky detection technique used to improve the performance of a previously developed partial differential equation (PDE)-based hazy image enhancement algorithm. Additionally, a proposed alternative method utilizes a function for log illumination refinement to improve de-hazing results while avoiding over-enhancement of sky or homogeneous regions. The algorithms were tested with several benchmark and calibration images and compared with several standard algorithms from the literature. Results indicate that the algorithms yield mostly consistent results and surpasses several of the other algorithms in terms of colour and contrast enhancement in addition to improved edge visibility.
Unsupervised distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution alignment relies either on minimizing simple non-parametric statistical distances such as maximum mean discrepancy, or on adversarial alignment. However, the former fails to capture the structure of complex real-world distributions, while the latter is difficult to train and does not provide any universal convergence guarantees or automatic quantitative validation procedures. In this paper we propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We show that, under certain assumptions, this combination yields a deep neural likelihood-based minimization objective that attains a known lower bound upon convergence. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
Cardiac motion estimation and segmentation play important roles in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In this paper, we propose a novel deep learning method for joint estimation of motion and segmentation from cardiac MR image sequences. The proposed network consists of two branches: a cardiac motion estimation branch which is built on a novel unsupervised Siamese style recurrent spatial transformer network, and a cardiac segmentation branch that is based on a fully convolutional network. In particular, a joint multi-scale feature encoder is learned by optimizing the segmentation branch and the motion estimation branch simultaneously. This enables the weakly-supervised segmentation by taking advantage of features that are unsupervisedly learned in the motion estimation branch from a large amount of unannotated data. Experimental results using cardiac MRI images from 220 subjects show that the joint learning of both tasks is complementary and the proposed models outperform the competing methods significantly in terms of accuracy and speed.
In this paper, we present a new robotic system to perform defect inspection tasks over free-form specular surfaces. The autonomous procedure is achieved by a six-DOF manipulator, equipped with a line scan camera and a high-intensity lighting system. Our method first uses the object's CAD mesh model to implement a K-means unsupervised learning algorithm that segments the object's surface into areas with similar curvature. Then, the scanning path is computed by using an adaptive algorithm that adjusts the camera's ROI to observe regions with irregular shapes properly. A novel iterative closest point-based projection registration method that robustly localizes the object in the robot's coordinate frame system is proposed to deal with the blind spot problem of specular objects captured by depth sensors. Finally, an image processing pipeline automatically detects surface defects in the captured high-resolution images. A detailed experimental study with a vision-guided robotic scanning system is reported to validate the proposed methodology.
Recent models for image processing are using the Convolutional neural network (CNN) which requires a pixel per pixel analysis of the input image. This method works well. However, it is time-consuming if we have large images. To increase the performance, by improving the training time or the accuracy, we need a size-independent method. As a solution, we can add a Neuronal Attention model (NAM). The power of this new approach is that it can efficiently choose several small regions from the initial image to focus on. The purpose of this paper is to explain and also test each of the NAM's parameters.
We establish the link between Mathematical Morphology and the map of Asplund's distances between a probe and a grey scale function, using the Logarithmic Image Processing scalar multiplication. We demonstrate that the map is the logarithm of the ratio between a dilation and an erosion of the function by a structuring function: the probe. The dilations and erosions are mappings from the lattice of the images into the lattice of the positive functions. Using a flat structuring element, the expression of the map of Asplund's distances can be simplified with a dilation and an erosion of the image; these mappings stays in the lattice of the images. We illustrate our approach by an example of pattern matching with a non-flat structuring function.
Hand pose estimation from 3D depth images, has been explored widely using various kinds of techniques in the field of computer vision. Though, deep learning based method improve the performance greatly recently, however, this problem still remains unsolved due to lack of large datasets, like ImageNet or effective data synthesis methods. In this paper, we propose HandAugment, a method to synthesize image data to augment the training process of the neural networks. Our method has two main parts: First, We propose a scheme of two-stage neural networks. This scheme can make the neural networks focus on the hand regions and thus to improve the performance. Second, we introduce a simple and effective method to synthesize data by combining real and synthetic image together in the image space. Finally, we show that our method achieves the first place in the task of depth-based 3D hand pose estimation in HANDS 2019 challenge.
The adoption of machine learning in critical contexts requires a reliable explanation of why the algorithm makes certain predictions. To address this issue, many methods have been proposed to explain the predictions of these black box models. Despite the choice of those many methods, little effort has been made to ensure that the explanations produced are objectively relevant. While it is possible to establish a number of desirable properties of a good explanation, it is more difficult to evaluate them. As a result, no measures are actually associated with the properties of consistency and generalization of explanations. We are introducing a new procedure to compute two new measures, Relative Consistency ReCo and Mean Generalization M eGe, respectively for consistency and generalization of explanations. Our results on several image classification datasets using progressively degraded models allow us to validate empirically the reliability of those measures. We compare the results obtained with those of existing measures. Finally we demonstrate the potential of the measures by applying them to different families of models, revealing an interesting link between gradient-based explanations methods and 1-Lipschitz networks.
Recent research finds CNN models for image classification demonstrate overlapped adversarial vulnerabilities: adversarial attacks can mislead CNN models with small perturbations, which can effectively transfer between different models trained on the same dataset. Adversarial training, as a general robustness improvement technique, eliminates the vulnerability in a single model by forcing it to learn robust features. The process is hard, often requires models with large capacity, and suffers from significant loss on clean data accuracy. Alternatively, ensemble methods are proposed to induce sub-models with diverse outputs against a transfer adversarial example, making the ensemble robust against transfer attacks even if each sub-model is individually non-robust. Only small clean accuracy drop is observed in the process. However, previous ensemble training methods are not efficacious in inducing such diversity and thus ineffective on reaching robust ensemble. We propose DVERGE, which isolates the adversarial vulnerability in each sub-model by distilling non-robust features, and diversifies the adversarial vulnerability to induce diverse outputs against a transfer attack. The novel diversity metric and training procedure enables DVERGE to achieve higher robustness against transfer attacks comparing to previous ensemble methods, and enables the improved robustness when more sub-models are added to the ensemble.