Rodrigo Minetto

White blood cell segmentation using morphological operators and scale-space analysis

This paper proposes a model-based methodology for recognizing and tracking objects in digital image sequences. Objects are represented by attributed relational graphs (or ARGs), which carry both local and relational information about them. The recognition is performed by inexact graph matching, which consists in finding an approximate homomorphism between ARGs derived from an input video and a model image. Searching for a suitable homomorphism is achieved through a tree-search optimization algorithm and the minimization of a pre-defined cost function. Motion smoothness between successive frames is exploited to achieve the recognition over the whole sequence, with improved spatio-temporal coherence.Cell segmentation is a challenging problem due to both the complex nature of the cells and the uncertainty present in video microscopy. Manual methods for this purpose are onerous, imprecise and highly subjective, thus requiring automated methods that perform this task in an objective and efficient way. In this paper, we propose a novel method to segment nucleus and cytoplasm of white blood cells (WBC). WBC composition of the blood provides important information to doctors and plays an important role in the diagnosis of different diseases. We use simple morphological operators and explore the scale-space properties of a toggle operator to improve the segmentation accuracy. The proposed scheme has been successfully applied to a large number of images, showing promising results for varying cell appearance and image quality, encouraging future works.

T-HOG: An effective gradient-based descriptor for single line text regions

We discuss the use of histogram of oriented gradients (HOG) descriptors as an effective tool for text description and recognition. Specifically, we propose a HOG-based texture descriptor (T-HOG) that uses a partition of the image into overlapping horizontal cells with gradual boundaries, to characterize single-line texts in outdoor scenes. The input of our algorithm is a rectangular image presumed to contain a single line of text in Roman-like characters. The output is a relatively short descriptor that provides an effective input to an SVM classifier. Extensive experiments show that the T-HOG is more accurate than Dalal and Triggss original HOG-based classifier, for any descriptor size. In addition, we show that the T-HOG is an effective tool for text/non-text discrimination and can be used in various text detection applications. In particular, combining T-HOG with a permissive bottom-up text detector is shown to outperform state-of-the-art text detection systems in two major publicly available databases.

Semiautomatic White Blood Cell Segmentation Based on Multiscale Analysis

This paper approaches novel methods to segment the nucleus and cytoplasm of white blood cells (WBC). This information is the basis to perform higher level tasks such as automatic differential counting, which plays an important role in the diagnosis of different diseases. We explore the image simplification and contour regularization resulting from the application of the selfdual multiscale morphological toggle (SMMT), an operator with scale-space properties. To segment the nucleus, the image preprocessing with SMMT has shown to be essential to ensure the accuracy of two well-known image segmentations techniques, namely, watershed transform and Level-Set methods. To identify the cytoplasm region, we propose two different schemes, based on granulometric analysis and on morphological transformations. The proposed methods have been successfully applied to a large number of images, showing promising segmentation and classification results for varying cell appearance and image quality, encouraging future works.

SnooperText: A Text Detection System for Automatic Indexing of Urban Scenes

We describe SnooperText, an original detector for textual information embedded in photos of building facades (such as names of stores, products and services) that we developed for the iTowns urban geographic information project. SnooperText locates candidate characters by using toggle-mapping image segmentation and character/non-character classification based on shape descriptors. The candidate characters are then grouped to form either candidate words or candidate text lines. These candidate regions are then validated by a text/non-text classifier using a HOG-based descriptor specifically tuned to single-line text regions. These operations are applied at multiple image scales in order to suppress irrelevant detail in character shapes and to avoid the use of overly large kernels in the segmentation. We show that SnooperText outperforms other published state-of-the-art text detection algorithms on standard image benchmarks. We also describe two metrics to evaluate the end-to-end performance of text extraction systems, and show that the use of SnooperText as a pre-filter significantly improves the performance of a general-purpose OCR algorithm when applied to photos of urban scenes.

Snoopertext: A multiresolution system for text detection in complex visual scenes

Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are then filtered out using shapebased classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results.

Adaptive edge-preserving image denoising using wavelet transforms

Image denoising is a relevant issue found in diverse image processing and computer vision problems. It is a challenge to preserve important features, such as edges, corners and other sharp structures, during the denoising process. Wavelet transforms have been widely used for image denoising since they provide a suitable basis for separating noisy signal from the image signal. This paper describes a novel image denoising method based on wavelet transforms to preserve edges. The decomposition is performed by dividing the image into a set of blocks and transforming the data into the wavelet domain. An adaptive thresholding scheme based on edge strength is used to effectively reduce noise while preserving important features of the original image. Experimental results, compared to other approaches, demonstrate that the proposed method is suitable for different classes of images contaminated by Gaussian noise.

Text detection and recognition in urban scenes

Text detection and recognition in real images taken in unconstrained environments, such as street view images, remain surprisingly challenging in Computer Vision.

Robust Estimation of Camera Motion Using Optical Flow Models

The estimation of camera motion is one of the most important aspects for video processing, analysis, indexing, and retrieval. Most of existing techniques to estimate camera motion are based on optical flow methods in the uncompressed domain. However, to decode and to analyze a video sequence is extremely time-consuming. Since video data are usually available in MPEG-compressed form, it is desirable to directly process video material without decoding. In this paper, we present a novel approach for estimating camera motion in MPEG video sequences. Our technique relies on linear combinations of optical flow models. The proposed method first creates prototypes of optical flow, and then performs a linear decomposition on the MPEG motion vectors, which is used to estimate the camera parameters. Experiments on synthesized and real-world video clips show that our technique is more effective than the state-of-the-art approaches for estimating camera motion in MPEG video sequences.

VEHICLE SPEED ESTIMATION BY LICENSE PLATE DETECTION AND TRACKING

We describe a novel system for vehicle speed estimation from videos captured in urban roadways. Our system uses text detection to locate the license plates of passing vehicles, which are then used to select stable features for tracking. The tracked features are then filtered and rectified for perspective distortion. Vehicle speed is estimated by comparing the trajectory of the tracked features to known real world measures. In experiments performed on videos captured under real operation conditions, our system attained a precision of 0.87 and a recall of 0.92 for license plate detection. Vehicle speeds were estimated with an average error of 0.59 km/h, staying inside the +2/-3 km/h limit, determined by regulatory authorities in several countries, in over 75% of the cases.

IFTrace: Video segmentation of deformable objects using the Image Foresting Transform

We introduce IFTrace, a method for video segmentation of deformable objects. The algorithm makes minimal assumptions about the nature of the tracked object: basically, that it consists of a few connected regions, and has a well-defined border. The objects to be tracked are interactively segmented in the first frame of the video, and a set of markers is then automatically selected in the interior and immediate surroundings of the object. These markers are then located in the next frame by a combination of KLT feature finding and motion extrapolation. Object boundaries are then identified from these markers by the Image Foresting Transform (IFT). These steps are repeated for all subsequent frames until the end of the movie. Thanks to the IFT and a special boundary detection operator, IFTrace can reliably track deformable objects in the presence of partial and total occlusions, camera motion, lighting and color changes, and other complications. Tests on real videos show that the IFT is better suited to this task than Graph-Cut methods, and that IFTrace is more robust than other state-of-the art algorithms - namely, the OpenCV Snake and CamShift algorithms, Hesss Particle-Filter, and Zhong and Changs method based on spatio-temporal consistency.