Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

We introduce a new top-down pipeline for scene text detection. We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization. The CCTN fast detects text regions roughly from a low-resolution image, and then accurately localizes text lines from each enlarged region. We cast previous character based detection into direct text region estimation, avoiding multiple bottom- up post-processing steps. It exhibits surprising robustness and discriminative power by considering whole text region as detection object which provides strong semantic information. We customize convolutional network by develop- ing rectangle convolutions and multiple in-network fusions. This enables it to handle multi-shape and multi-scale text efficiently. Furthermore, the CCTN is computationally efficient by sharing convolutional computations, and high-level property allows it to be invariant to various languages and multiple orientations. It achieves 0.84 and 0.86 F-measures on the ICDAR 2011 and ICDAR 2013, delivering substantial improvements over state-of-the-art results [23, 1].

Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches

Modern approaches to pose and body shape estimation have recently achieved strong performance even under challenging real-world conditions. Even from a single image of a clothed person, a realistic looking body shape can be inferred that captures a users' weight group and body shape type well. This opens up a whole spectrum of applications -- in particular in fashion -- where virtual try-on and recommendation systems can make use of these new and automatized cues. However, a realistic depiction of the undressed body is regarded highly private and therefore might not be consented by most people. Hence, we ask if the automatic extraction of such information can be effectively evaded. While adversarial perturbations have been shown to be effective for manipulating the output of machine learning models -- in particular, end-to-end deep learning approaches -- state of the art shape estimation methods are composed of multiple stages. We perform the first investigation of different strategies that can be used to effectively manipulate the automatic shape estimation while preserving the overall appearance of the original image.

Picture What you Read

Visualization refers to our ability to create an image in our head based on the text we read or the words we hear. It is one of the many skills that makes reading comprehension possible. Convolutional Neural Networks (CNN) are an excellent tool for recognizing and classifying text documents. In addition, it can generate images conditioned on natural language. In this work, we utilize CNNs capabilities to generate realistic images representative of the text illustrating the semantic concept. We conducted various experiments to highlight the capacity of the proposed model to generate representative images of the text descriptions used as input to the proposed model.

Image patch analysis of sunspots and active regions. I. Intrinsic dimension and correlation analysis

The flare-productivity of an active region is observed to be related to its spatial complexity. Mount Wilson or McIntosh sunspot classifications measure such complexity but in a categorical way, and may therefore not use all the information present in the observations. Moreover, such categorical schemes hinder a systematic study of an active region's evolution for example. We propose fine-scale quantitative descriptors for an active region's complexity and relate them to the Mount Wilson classification. We analyze the local correlation structure within continuum and magnetogram data, as well as the cross-correlation between continuum and magnetogram data. We compute the intrinsic dimension, partial correlation, and canonical correlation analysis (CCA) of image patches of continuum and magnetogram active region images taken from the SOHO-MDI instrument. We use masks of sunspots derived from continuum as well as larger masks of magnetic active regions derived from the magnetogram to analyze separately the core part of an active region from its surrounding part. We find the relationship between complexity of an active region as measured by Mount Wilson and the intrinsic dimension of its image patches. Partial correlation patterns exhibit approximately a third-order Markov structure. CCA reveals different patterns of correlation between continuum and magnetogram within the sunspots and in the region surrounding the sunspots. These results also pave the way for patch-based dictionary learning with a view towards automatic clustering of active regions.

Efficient Computation of Hessian Matrices in TensorFlow

The Hessian matrix has a number of important applications in a variety of different fields, such as optimzation, image processing and statistics. In this paper we focus on the practical aspects of efficiently computing Hessian matrices in the context of deep learning using the Python scripting language and the TensorFlow library.

Object Segmentation Tracking from Generic Video Cues

We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of dedicated CNN architectures, we show the potential of a variational model, based on generic video information from motion and color. Such cues are usually required for tasks such as robot navigation or grasp estimation. We leverage them directly for video object segmentation and thus provide accurate segmentations at potentially very low extra cost. Furthermore, we show that our approach can be combined with state-of-the-art CNN-based segmentations in order to improve over their respective results. We evaluate our method on the datasets DAVIS16,17 and SegTrack v2.

Unsupervised Learning Methods for Visual Place Recognition in Discretely and Continuously Changing Environments

Visual place recognition in changing environments is the problem of finding matchings between two sets of observations, a query set and a reference set, despite severe appearance changes. Recently, image comparison using CNN-based descriptors showed very promising results. However, existing experiments from the literature typically assume a single distinctive condition within each set (e.g., reference: day, query: night). We demonstrate that as soon as the conditions change within one set (e.g., reference: day, query: traversal daytime-dusk-night-dawn), different places under the same condition can suddenly look more similar than same places under different conditions and state-of-the-art approaches like CNN-based descriptors fail. This paper discusses this practically very important problem of in-sequence condition changes and defines a hierarchy of problem setups from (1) no in-sequence changes, (2) discrete in-sequence changes, to (3) continuous in-sequence changes. We will experimentally evaluate the effect of these changes on two state-of-the-art CNN-descriptors. Our experiments emphasize the importance of statistical standardization of descriptors and shows its limitations in case of continuous changes. To address this practically most relevant setup, we investigate and experimentally evaluate the application of unsupervised learning methods using two available PCA-based approaches and propose a novel clustering-based extension of the statistical normalization.

Deep Variable-Block Chain with Adaptive Variable Selection

The architectures of deep neural networks (DNN) rely heavily on the underlying grid structure of variables, for instance, the lattice of pixels in an image. For general high dimensional data with variables not associated with a grid, the multi-layer perceptron and deep brief network are often used. However, it is frequently observed that those networks do not perform competitively and they are not helpful for identifying important variables. In this paper, we propose a framework that imposes on blocks of variables a chain structure obtained by step-wise greedy search so that the DNN architecture can leverage the constructed grid. We call this new neural network Deep Variable-Block Chain (DVC). Because the variable blocks are used for classification in a sequential manner, we further develop the capacity of selecting variables adaptively according to a number of regions trained by a decision tree. Our experiments show that DVC outperforms other generic DNNs and other strong classifiers. Moreover, DVC can achieve high accuracy at much reduced dimensionality and sometimes reveals drastically different sets of relevant variables for different regions.

Intensity and Rescale Invariant Copy Move Forgery Detection Techniques

In this contemporary world digital media such as videos and images behave as an active medium to carry valuable information across the globe on all fronts. However there are several techniques evolved to tamper the image which has made their authenticity untrustworthy. CopyMove Forgery CMF is one of the most common forgeries present in an image where a cluster of pixels are duplicated in the same image with potential postprocessing techniques. Various state-of-art techniques are developed in the recent years which are effective in detecting passive image forgery. However most methods do fail when the copied image is rescaled or added with certain intensity before being pasted due to de-synchronization of pixels in the searching process. To tackle this problem the paper proposes distinct novel algorithms which recognize a unique approach of using Hus invariant moments and Discreet Cosine Transformations DCT to attain the desired rescale invariant and intensity invariant CMF detection techniques respectively. The experiments conducted quantitatively and qualitatively demonstrate the effectiveness of the algorithm.

A Machine-learning framework for automatic reference-free quality assessment in MRI

Magnetic resonance (MR) imaging offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual process and therefore time- and cost-intensive. Any imaging artifacts originating from scanner hardware, signal processing or induced by the patient may reduce the image quality and complicate the diagnosis or any image post-processing. Therefore, the assessment or the ensurance of sufficient image quality in an automated manner is of high interest. Usually no reference image is available or difficult to define. Therefore, classical reference-based approaches are not applicable. Model observers mimicking the human observers (HO) can assist in this task. Thus, we propose a new machine-learning-based reference-free MR image quality assessment framework which is trained on HO-derived labels to assess MR image quality immediately after each acquisition. We include the concept of active learning and present an efficient blinded reading platform to reduce the effort in the HO labeling procedure. Derived image features and the applied classifiers (support-vector-machine, deep neural network) are investigated for a cohort of 250 patients. The MR image quality assessment framework can achieve a high test accuracy of 93.7$\%$ for estimating quality classes on a 5-point Likert-scale. The proposed MR image quality assessment framework is able to provide an accurate and efficient quality estimation which can be used as a prospective quality assurance including automatic acquisition adaptation or guided MR scanner operation, and/or as a retrospective quality assessment including support of diagnostic decisions or quality control in cohort studies.