Many cultures around the world believe that palm reading can be used to predict the future life of a person. Palmistry uses features of the hand such as palm lines, hand shape, or fingertip position. However, the research on palm-line detection is still scarce, many of them applied traditional image processing techniques. In most real-world scenarios, images usually are not in well-conditioned, causing these methods to severely under-perform. In this paper, we propose an algorithm to extract principle palm lines from an image of a person's hand. Our method applies deep learning networks (DNNs) to improve performance. Another challenge of this problem is the lack of training data. To deal with this issue, we handcrafted a dataset from scratch. From this dataset, we compare the performance of readily available methods with ours. Furthermore, based on the UNet segmentation neural network architecture and the knowledge of attention mechanism, we propose a highly efficient architecture to detect palm-lines. We proposed the Context Fusion Module to capture the most important context feature, which aims to improve segmentation accuracy. The experimental results show that it outperforms the other methods with the highest F1 Score about 99.42% and mIoU is 0.584 for the same dataset.
Text lines are important parts of handwritten document images and easier to analyze by further applications. Despite recent progress in text line detection, text line extraction from a handwritten document remains an unsolved task. This paper proposes to use a fully convolutional network for text line detection and energy minimization for text line extraction. Detected text lines are represented by blob lines that strike through the text lines. These blob lines assist an energy function for text line extraction. The detection stage can locate arbitrarily oriented text lines. Furthermore, the extraction stage is capable of finding out the pixels of text lines with various heights and interline proximity independent of their orientations. Besides, it can finely split the touching and overlapping text lines without an orientation assumption. We evaluate the proposed method on VML-AHTE, VML-MOC, and Diva-HisDB datasets. The VML-AHTE dataset contains overlapping, touching and close text lines with rich diacritics. The VML-MOC dataset is very challenging by its multiply oriented and skewed text lines. The Diva-HisDB dataset exhibits distinct text line heights and touching text lines. The results demonstrate the effectiveness of the method despite various types of challenges, yet using the same parameters in all the experiments.
In the application of computer-vision based displacement measurement, an optical target is usually required to prove the reference. In the case that the optical target cannot be attached to the measuring objective, edge detection, feature matching and template matching are the most common approaches in target-less photogrammetry. However, their performance significantly relies on parameter settings. This becomes problematic in dynamic scenes where complicated background texture exists and varies over time. To tackle this issue, we propose virtual point tracking for real-time target-less dynamic displacement measurement, incorporating deep learning techniques and domain knowledge. Our approach consists of three steps: 1) automatic calibration for detection of region of interest; 2) virtual point detection for each video frame using deep convolutional neural network; 3) domain-knowledge based rule engine for point tracking in adjacent frames. The proposed approach can be executed on an edge computer in a real-time manner (i.e. over 30 frames per second). We demonstrate our approach for a railway application, where the lateral displacement of the wheel on the rail is measured during operation. We also implement an algorithm using template matching and line detection as the baseline for comparison. The numerical experiments have been performed to evaluate the performance and the latency of our approach in the harsh railway environment with noisy and varying backgrounds.
Deep Learning (DL) based methods for object detection achieve remarkable performance at the cost of computationally expensive training and extensive data labeling. Robots embodiment can be exploited to mitigate this burden by acquiring automatically annotated training data via a natural interaction with a human showing the object of interest, handheld. However, learning solely from this data may introduce biases (the so-called domain shift), and prevents adaptation to novel tasks. While Weakly-supervised Learning (WSL) offers a well-established set of techniques to cope with these problems in general-purpose Computer Vision, its adoption in challenging robotic domains is still at a preliminary stage. In this work, we target the scenario of a robot trained in a teacher-learner setting to detect handheld objects. The aim is to improve detection performance in different settings by letting the robot explore the environment with a limited human labeling budget. We compare several techniques for WSL in detection pipelines to reduce model re-training costs without compromising accuracy, proposing solutions which target the considered robotic scenario. We show that the robot can improve adaptation to novel domains, either by interacting with a human teacher (Active Learning) or with an autonomous supervision (Semi-supervised Learning). We integrate our strategies into an on-line detection method, achieving efficient model update capabilities with few labels. We experimentally benchmark our method on challenging robotic object detection tasks under domain shift.
In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained from scratch for detecting objects from historical documents. We consider the line segmentation task and more generally the layout analysis problem as a pixel-wise classification task then our model outputs a pixel-labeling of the input images. We show that Doc-UFCN outperforms state-of-the-art methods on various datasets and also demonstrate that the pre-trained parts on natural scene images are not required to reach good results. In addition, we show that pre-training on multiple document datasets can improve the performances. We evaluate the models using various metrics to have a fair and complete comparison between the methods.
We introduce in this paper a new dataset of annotated pages from books of hours, a type of handwritten prayer books owned and used by rich lay people in the late middle ages. The dataset was created for conducting historical research on the evolution of the religious mindset in Europe at this period since the book of hours represent one of the major sources of information thanks both to their rich illustrations and the different types of religious sources they contain. We first describe how the corpus was collected and manually annotated then present the evaluation of a state-of-the-art system for text line detection and for zone detection and typing. The corpus is freely available for research.
Line detection is an important computer vision task traditionally solved by Hough Transform. With the advance of deep learning, however, trainable approaches to line detection became popular. In this paper we propose a lightweight CNN for line detection with an embedded parameter-free Hough layer, which allows the network neurons to have global strip-like receptive fields. We argue that traditional convolutional networks have two inherent problems when applied to the task of line detection and show how insertion of a Hough layer into the network solves them. Additionally, we point out some major inconsistencies in the current datasets used for line detection.
We have developed a framework for crisis response and management that incorporates the latest technologies in computer vision (CV), inland flood prediction, damage assessment and data visualization. The framework uses data collected before, during, and after the crisis to enable rapid and informed decision making during all phases of disaster response. Our computer-vision model analyzes spaceborne and airborne imagery to detect relevant features during and after a natural disaster and creates metadata that is transformed into actionable information through web-accessible mapping tools. In particular, we have designed an ensemble of models to identify features including water, roads, buildings, and vegetation from the imagery. We have investigated techniques to bootstrap and reduce dependency on large data annotation efforts by adding use of open source labels including OpenStreetMaps and adding complementary data sources including Height Above Nearest Drainage (HAND) as a side channel to the network's input to encourage it to learn other features orthogonal to visual characteristics. Modeling efforts include modification of connected U-Nets for (1) semantic segmentation, (2) flood line detection, and (3) for damage assessment. In particular for the case of damage assessment, we added a second encoder to U-Net so that it could learn pre-event and post-event image features simultaneously. Through this method, the network is able to learn the difference between the pre- and post-disaster images, and therefore more effectively classify the level of damage. We have validated our approaches using publicly available data from the National Oceanic and Atmospheric Administration (NOAA)'s Remote Sensing Division, which displays the city and street-level details as mosaic tile images as well as data released as part of the Xview2 challenge.
In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named character branch and layout branch are added behind the feature extraction network. The character branch localizes individual characters in a document image and recognizes them simultaneously. Then we adopt a post-processing method to group them into text lines. The layout branch based on fully convolutional network outputs a binary mask. We then use Hough transform for line detection on the binary mask and combine character results with the layout information to restore document content. These two branches can be trained in parallel and are easy to train. Furthermore, we propose a re-score mechanism to minimize recognition error. Experiment results on the extended Chinese historical document MTHv2 dataset demonstrate the effectiveness of the proposed framework.
Airborne light detection and ranging (LiDAR) plays an increasingly significant role in urban planning, topographic mapping, environmental monitoring, power line detection and other fields thanks to its capability to quickly acquire large-scale and high-precision ground information. To achieve point cloud classification, previous studies proposed point cloud deep learning models that can directly process raw point clouds based on PointNet-like architectures. And some recent works proposed graph convolution neural network based on the inherent topology of point clouds. However, the above point cloud deep learning models only pay attention to exploring local geometric structures, yet ignore global contextual relationships among all points. In this paper, we present a graph attention convolution neural network (GACNN) that can be directly applied to the classification of unstructured 3D point clouds obtained by airborne LiDAR. Specifically, we first introduce a graph attention convolution module that incorporates global contextual information and local structural features. Based on the proposed graph attention convolution module, we further design an end-to-end encoder-decoder network, named GACNN, to capture multiscale features of the point clouds and therefore enable more accurate airborne point cloud classification. Experiments on the ISPRS 3D labeling dataset show that the proposed model achieves a new state-of-the-art performance in terms of average F1 score (71.5\%) and a satisfying overall accuracy (83.2\%). Additionally, experiments further conducted on the 2019 Data Fusion Contest Dataset by comparing with other prevalent point cloud deep learning models demonstrate the favorable generalization capability of the proposed model.
Botnets are increasingly used by malicious actors, creating increasing threat to a large number of internet users. To address this growing danger, we propose to study methods to detect botnets, especially those that are hard to capture with the commonly used methods, such as the signature based ones and the existing anomaly-based ones. More specifically, we propose a novel machine learning based method, named Recurrent Variational Autoencoder (RVAE), for detecting botnets through sequential characteristics of network traffic flow data including attacks by botnets. We validate robustness of our method with the CTU-13 dataset, where we have chosen the testing dataset to have different types of botnets than those of training dataset. Tests show that RVAE is able to detect botnets with the same accuracy as the best known results published in literature. In addition, we propose an approach to assign anomaly score based on probability distributions, which allows us to detect botnets in streaming mode as the new networking statistics becomes available. This on-line detection capability would enable real-time detection of unknown botnets.
We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e. non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features eg features along lines close to a specific line, that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives.
Line segment detection is an essential task in computer vision and image analysis, as it is the critical foundation for advanced tasks such as shape modeling and road lane line detection for autonomous driving. We present a robust topological graph guided approach for line segment detection in low quality binary images (hence, we call it TGGLines). Due to the graph-guided approach, TGGLines not only detects line segments, but also organizes the segments with a line segment connectivity graph, which means the topological relationships (e.g., intersection, an isolated line segment) of the detected line segments are captured and stored; whereas other line detectors only retain a collection of loose line segments. Our empirical results show that the TGGLines detector visually and quantitatively outperforms state-of-the-art line segment detection methods. In addition, our TGGLines approach has the following two competitive advantages: (1) our method only requires one parameter and it is adaptive, whereas almost all other line segment detection methods require multiple (non-adaptive) parameters, and (2) the line segments detected by TGGLines are organized by a line segment connectivity graph.
Perception techniques for autonomous driving should be adaptive to various environments. In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and computing power of the target system. To address these problems, in this paper, we propose a traffic line detection method called Point Instance Network (PINet); the method is based on the key points estimation and instance segmentation approach. The PINet includes several stacked hourglass networks that are trained simultaneously. Therefore the size of the trained models can be chosen according to the computing power of the target environment. We cast a clustering problem of the predicted key points as an instance segmentation problem; the PINet can be trained regardless of the number of the traffic lines. The PINet achieves competitive accuracy and false positive on the TuSimple and Culane datasets, popular public datasets for lane detection. Our code is available at https://github.com/koyeongmin/PINet_new
Chinese keyword spotting is a challenging task as there is no visual blank for Chinese words. Different from English words which are split naturally by visual blanks, Chinese words are generally split only by semantic information. In this paper, we propose a new Chinese keyword spotter for natural images, which is inspired by Mask R-CNN. We propose to predict the keyword masks guided by text line detection. Firstly, proposals of text lines are generated by Faster R-CNN;Then, text line masks and keyword masks are predicted by segmentation in the proposals. In this way, the text lines and keywords are predicted in parallel. We create two Chinese keyword datasets based on RCTW-17 and ICPR MTWI2018 to verify the effectiveness of our method.
Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinesecharacters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4. The official website for the competition is http://rrc.cvc.uab.es/?ch=12.
In low-altitude Unmanned Aerial Vehicle (UAV) flights, power lines are considered as one of the most threatening hazards and one of the most difficult obstacles to avoid. In recent years, many vision-based techniques have been proposed to detect power lines to facilitate self-driving UAVs and automatic obstacle avoidance. However, most of the proposed methods are typically based on a common three-step approach: (i) edge detection, (ii) the Hough transform, and (iii) spurious line elimination based on power line constrains. These approaches not only are slow and inaccurate but also require a huge amount of effort in post-processing to distinguish between power lines and spurious lines. In this paper, we introduce LS-Net, a fast single-shot line-segment detector, and apply it to power line detection. The LS-Net is by design fully convolutional and consists of three modules: (i) a fully convolutional feature extractor, (ii) a classifier, and (iii) a line segment regressor. Due to the unavailability of large datasets with annotations of power lines, we render synthetic images of power lines using the Physically Based Rendering (PBR) approach and propose a series of effective data augmentation techniques to generate more training data. With a customized version of the VGG-16 network as the backbone, the proposed approach outperforms existing state-of-the-art approaches. In addition, the LS-Net can detect power lines in near real-time (20.4 FPS). This suggests that our proposed approach has a promising role in automatic obstacle avoidance and as a valuable component of self-driving UAVs, especially for automatic autonomous power line inspection.
This paper investigates the problem of dim frequency line detection and recovery in the so-called lofargram. Theoretically, time integration long enough can always enhance the detection characteristic. But this does not hold for irregularly fluctuating lines. Deep learning has been shown to perform very well for sophisticated visual inference tasks. With the composition of multiple processing layers, very complex high level representation that amplify the important aspects of input while suppresses irrelevant variations can be learned. Hence we propose a new DeepLofargram, composed of deep convolutional neural network and its visualization counterpart. Plugging into specifically designed multi-task loss, an end-to-end training jointly learns to detect and recover the spatial location of potential lines. Leveraging on this deep architecture, the performance boundary is -24dB on average, and -26dB for some. This is far beyond the perception of human visual and significantly improves the state-of-the-art.
With the rapid development of information and communication technology (ICT), taxi business becomes a typical electronic commerce mode. However, one traditional problem still exists in taxi service, that greedy taxi drivers may deliberately take unnecessary detours to overcharge passengers. The detection of these fraudulent behaviors is essential to ensure high-quality taxi service. In this paper, we propose a novel framework for detecting and analyzing the detour behaviors both in off-line database and among on-line trips. Applying our framework to real-world taxi data-set, a remarkable performance (AUC surpasses 0.98) has been achieved in off-line classification. Meanwhile, we further extend the off-line methods to on-line detection, a warning mechanism is introduced to remind drivers and an excellent precision (AUC surpasses 0.90) also has arrived in this phases. After conducting extensive experiments to verify the relationships between pricing regulations and detour behaviors, some quantitative pricing suggestions, including rising base fare and reducing distance-based fare rate, are provided to eliminate detour behaviors from the long term.
Edge detection is widely and fundamental feature used in various algorithms in computer vision to determine the edges in an image. The edge detection algorithm is used to determine the edges in an image which are further used by various algorithms from line detection to machine learning that can determine objects based on their contour. Inspired by new convolution techniques in machine learning we discuss here the idea of extending the standard Sobel kernels, which are used to compute the gradient of an image in order to find its edges. We compare the result of our custom extended filters with the results of the standard Sobel filter and other edge detection filters using different image sets and algorithms. We present statistical results regarding the custom extended Sobel filters improvements.