|
|
Suman Ghosh, & Ernest Valveny. (2017). R-PHOC: Segmentation-Free Word Spotting using CNN. In 14th International Conference on Document Analysis and Recognition.
Abstract: arXiv:1707.01294
This paper proposes a region based convolutional neural network for segmentation-free word spotting. Our network takes as input an image and a set of word candidate bound- ing boxes and embeds all bounding boxes into an embedding space, where word spotting can be casted as a simple nearest neighbour search between the query representation and each of the candidate bounding boxes. We make use of PHOC embedding as it has previously achieved significant success in segmentation- based word spotting. Word candidates are generated using a simple procedure based on grouping connected components using some spatial constraints. Experiments show that R-PHOC which operates on images directly can improve the current state-of- the-art in the standard GW dataset and performs as good as PHOCNET in some cases designed for segmentation based word spotting.
Keywords: Convolutional neural network; Image segmentation; Artificial neural network; Nearest neighbor search
|
|
|
|
Xialei Liu, Joost Van de Weijer, & Andrew Bagdanov. (2017). RankIQA: Learning from Rankings for No-reference Image Quality Assessment. In 17th IEEE International Conference on Computer Vision.
Abstract: We propose a no-reference image quality assessment (NR-IQA) approach that learns from rankings (RankIQA). To address the problem of limited IQA dataset size, we train a Siamese Network to rank images in terms of image quality by using synthetically generated distortions for which relative image quality is known. These ranked image sets can be automatically generated without laborious human labeling. We then use fine-tuning to transfer the knowledge represented in the trained Siamese Network to a traditional CNN that estimates absolute image quality from single images. We demonstrate how our approach can be made significantly more efficient than traditional Siamese Networks by forward propagating a batch of images through a single network and backpropagating gradients derived from all pairs of images in the batch. Experiments on the TID2013 benchmark show that we improve the state-of-the-art by over 5%. Furthermore, on the LIVE benchmark we show that our approach is superior to existing NR-IQA techniques and that we even outperform the state-of-the-art in full-reference IQA (FR-IQA) methods without having to resort to high-quality reference images to infer IQA.
|
|
|
|
Leonardo Galteri, Dena Bazazian, Lorenzo Seidenari, Marco Bertini, Andrew Bagdanov, Anguelos Nicolaou, et al. (2017). Reading Text in the Wild from Compressed Images. In 1st International workshop on Egocentric Perception, Interaction and Computing.
Abstract: Reading text in the wild is gaining attention in the computer vision community. Images captured in the wild are almost always compressed to varying degrees, depending on application context, and this compression introduces artifacts
that distort image content into the captured images. In this paper we investigate the impact these compression artifacts have on text localization and recognition in the wild. We also propose a deep Convolutional Neural Network (CNN) that can eliminate text-specific compression artifacts and which leads to an improvement in text recognition. Experimental results on the ICDAR-Challenge4 dataset demonstrate that compression artifacts have a significant
impact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates.
|
|
|
|
Quentin Angermann, Jorge Bernal, Cristina Sanchez Montes, Maroua Hammami, Gloria Fernandez Esparrach, Xavier Dray, et al. (2017). Real-Time Polyp Detection in Colonoscopy Videos: A Preliminary Study For Adapting Still Frame-based Methodology To Video Sequences Analysis. In 31st International Congress and Exhibition on Computer Assisted Radiology and Surgery.
|
|
|
|
Pau Rodriguez, Jordi Gonzalez, Jordi Cucurull, Josep M. Gonfaus, & Xavier Roca. (2017). Regularizing CNNs with Locally Constrained Decorrelations. In 5th International Conference on Learning Representations.
|
|
|
|
Jun Wan, Sergio Escalera, Gholamreza Anbarjafari, Hugo Jair Escalante, Xavier Baro, Isabelle Guyon, et al. (2017). Results and Analysis of ChaLearn LAP Multi-modal Isolated and ContinuousGesture Recognition, and Real versus Fake Expressed Emotions Challenges. In Chalearn Workshop on Action, Gesture, and Emotion Recognition: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions at ICCV.
Abstract: We analyze the results of the 2017 ChaLearn Looking at People Challenge at ICCV. The challenge comprised three tracks: (1) large-scale isolated (2) continuous gesture recognition, and (3) real versus fake expressed emotions tracks. It is the second round for both gesture recognition challenges, which were held first in the context of the ICPR 2016 workshop on “multimedia challenges beyond visual analysis”. In this second round, more participants joined the competitions, and the performances considerably improved compared to the first round. Particularly, the best recognition accuracy of isolated gesture recognition has improved from 56.90% to 67.71% in the IsoGD test set, and Mean Jaccard Index (MJI) of continuous gesture recognition has improved from 0.2869 to 0.6103 in the ConGD test set. The third track is the first challenge on real versus fake expressed emotion classification, including six emotion categories, for which a novel database was introduced. The first place was shared between two teams who achieved 67.70% averaged recognition rate on the test set. The data of the three tracks, the participants' code and method descriptions are publicly available to allow researchers to keep making progress in the field.
|
|
|
|
Cristhian Aguilera, Xavier Soria, Angel Sappa, & Ricardo Toledo. (2017). RGBN Multispectral Images: a Novel Color Restoration Approach. In 15th International Conference on Practical Applications of Agents and Multi-Agent System.
Abstract: This paper describes a color restoration technique used to remove NIR information from single sensor cameras where color and near-infrared images are simultaneously acquired|referred to in the literature as RGBN images. The proposed approach is based on a neural network architecture that learns the NIR information contained in the RGBN images. The proposed approach is evaluated on real images obtained by using a pair of RGBN cameras. Additionally, qualitative comparisons with a nave color correction technique based on mean square
error minimization are provided.
Keywords: Multispectral Imaging; Free Sensor Model; Neural Network
|
|
|
|
Laura Lopez-Fuentes, Claudio Rossi, & Harald Skinnemoen. (2017). River segmentation for flood monitoring. In Data Science for Emergency Management at Big Data 2017.
Abstract: Floods are major natural disasters which cause deaths and material damages every year. Monitoring these events is crucial in order to reduce both the affected people and the economic losses. In this work we train and test three different Deep Learning segmentation algorithms to estimate the water area from river images, and compare their performances. We discuss the implementation of a novel data chain aimed to monitor river water levels by automatically process data collected from surveillance cameras, and to give alerts in case of high increases of the water level or flooding. We also create and openly publish the first image dataset for river water segmentation.
|
|
|
|
Sounak Dey, Palaiahnakote Shivakumara, K.S. Raghunanda, Umapada Pal, Tong Lu, G. Hemantha Kumar, et al. (2017). Script independent approach for multi-oriented text detection in scene image. NEUCOM - Neurocomputing, 242, 96–112.
Abstract: Developing a text detection method which is invariant to scripts in natural scene images is a challeng- ing task due to different geometrical structures of various scripts. Besides, multi-oriented of text lines in natural scene images make the problem more challenging. This paper proposes to explore ring radius transform (RRT) for text detection in multi-oriented and multi-script environments. The method finds component regions based on convex hull to generate radius matrices using RRT. It is a fact that RRT pro- vides low radius values for the pixels that are near to edges, constant radius values for the pixels that represent stroke width, and high radius values that represent holes created in background and convex hull because of the regular structures of text components. We apply k -means clustering on the radius matrices to group such spatially coherent regions into individual clusters. Then the proposed method studies the radius values of such cluster components that are close to the centroid and far from the cen- troid to detect text components. Furthermore, we have developed a Bangla dataset (named as ISI-UM dataset) and propose a semi-automatic system for generating its ground truth for text detection of arbi- trary orientations, which can be used by the researchers for text detection and recognition in the future. The ground truth will be released to public. Experimental results on our ISI-UM data and other standard datasets, namely, ICDAR 2013 scene, SVT and MSRA data, show that the proposed method outperforms the existing methods in terms of multi-lingual and multi-oriented text detection ability.
|
|
|
|
Lluis Gomez, Y. Patel, Marçal Rusiñol, C.V. Jawahar, & Dimosthenis Karatzas. (2017). Self‐supervised learning of visual features through embedding images into text topic spaces. In 30th IEEE Conference on Computer Vision and Pattern Recognition.
Abstract: End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.
|
|
|
|
German Ros, Laura Sellart, Gabriel Villalonga, Elias Maidanik, Francisco Molero, Marc Garcia, et al. (2017). Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA. In Gabriela Csurka (Ed.), Domain Adaptation in Computer Vision Applications (Vol. 12, pp. 227–241). Springer.
Abstract: Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. Recent revolutionary results of deep convolutional neural networks (DCNNs) foreshadow the advent of reliable classifiers to perform such visual tasks. However, DCNNs require learning of many parameters from raw images; thus, having a sufficient amount of diverse images with class annotations is needed. These annotations are obtained via cumbersome, human labour which is particularly challenging for semantic segmentation since pixel-level annotations are required. In this chapter, we propose to use a combination of a virtual world to automatically generate realistic synthetic images with pixel-level annotations, and domain adaptation to transfer the models learnt to correctly operate in real scenarios. We address the question of how useful synthetic data can be for semantic segmentation – in particular, when using a DCNN paradigm. In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations and object identifiers. We use SYNTHIA in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments with DCNNs that show that combining SYNTHIA with simple domain adaptation techniques in the training stage significantly improves performance on semantic segmentation.
Keywords: SYNTHIA; Virtual worlds; Autonomous Driving
|
|
|
|
Aniol Lidon, Marc Bolaños, Mariella Dimiccoli, Petia Radeva, Maite Garolera, & Xavier Giro. (2017). Semantic Summarization of Egocentric Photo-Stream Events. In 2nd Workshop on Lifelogging Tools and Applications.
|
|
|
|
Sounak Dey, Anjan Dutta, Josep Llados, Alicia Fornes, & Umapada Pal. (2017). Shallow Neural Network Model for Hand-drawn Symbol Recognition in Multi-Writer Scenario. In 14th International Conference on Document Analysis and Recognition (pp. 31–32).
Abstract: One of the main challenges in hand drawn symbol recognition is the variability among symbols because of the different writer styles. In this paper, we present and discuss some results recognizing hand-drawn symbols with a shallow neural network. A neural network model inspired from the LeNet architecture has been used to achieve state-of-the-art results with
very less training data, which is very unlikely to the data hungry deep neural network. From the results, it has become evident that the neural network architectures can efficiently describe and recognize hand drawn symbols from different writers and can model the inter author aberration
|
|
|
|
Daniel Hernandez, Lukas Schneider, Antonio Espinosa, David Vazquez, Antonio Lopez, Uwe Franke, et al. (2017). Slanted Stixels: Representing San Francisco's Steepest Streets. In 28th British Machine Vision Conference.
Abstract: In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced that uses an extremely efficient over-segmentation. In doing so, the computational complexity of the Stixel inference algorithm is reduced significantly, achieving real-time computation capabilities with only a slight drop in accuracy. We evaluate the proposed approach in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.
|
|
|
|
J. Chazalon, P. Gomez-Kramer, Jean-Christophe Burie, M.Coustaty, S.Eskenazi, Muhammad Muzzamil Luqman, et al. (2017). SmartDoc 2017 Video Capture: Mobile Document Acquisition in Video Mode. In 1st International Workshop on Open Services and Tools for Document Analysis.
Abstract: As mobile document acquisition using smartphones is getting more and more common, along with the continuous improvement of mobile devices (both in terms of computing power and image quality), we can wonder to which extent mobile phones can replace desktop scanners. Modern applications can cope with perspective distortion and normalize the contrast of a document page captured with a smartphone, and in some cases like bottle labels or posters, smartphones even have the advantage of allowing the acquisition of non-flat or large documents. However, several cases remain hard to handle, such as reflective documents (identity cards, badges, glossy magazine cover, etc.) or large documents for which some regions require an important amount of detail. This paper introduces the SmartDoc 2017 benchmark (named “SmartDoc Video Capture”), which aims at
assessing whether capturing documents using the video mode of a smartphone could solve those issues. The task under evaluation is both a stitching and a reconstruction problem, as the user can move the device over different parts of the document to capture details or try to erase highlights. The material released consists of a dataset, an evaluation method and the associated tool, a sample method, and the tools required to extend the dataset. All the components are released publicly under very permissive licenses, and we particularly cared about maximizing the ease of
understanding, usage and improvement.
|
|
