Texture for Script identification

The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.

Using text-spotting to query the world

The world we live in is well labeled for the benefit of humans but to date robots have made little use of this resource. In this paper we describe a system that allows robots to read and interpret visible text and use it to understand the content of the scene. We use a generative probabilistic model that explains spotted text in terms of arbitrary search terms. This allows the robot to understand the underlying function of the scene it is looking at, such as whether it is a bank or a restaurant. We describe the text spotting engine at the heart of our system that is able to detect and parse wild text in images, and the generative model, and present results from images obtained with a robot in a busy city setting.

The impact of OCR accuracy on automated cancer classification of pathology reports

Objective To evaluate the effects of Optical Character Recognition (OCR) on the automatic cancer classification of pathology reports. Method Scanned images of pathology reports were converted to electronic free-text using a commercial OCR system. A state-of-the-art cancer classification system, the Medical Text Extraction (MEDTEX) system, was used to automatically classify the OCR reports. Classifications produced by MEDTEX on the OCR versions of the reports were compared with the classification from a human amended version of the OCR reports. Results The employed OCR system was found to recognise scanned pathology reports with up to 99.12% character accuracy and up to 98.95% word accuracy. Errors in the OCR processing were found to minimally impact on the automatic classification of scanned pathology reports into notifiable groups. However, the impact of OCR errors is not negligible when considering the extraction of cancer notification items, such as primary site, histological type, etc. Conclusions The automatic cancer classification system used in this work, MEDTEX, has proven to be robust to errors produced by the acquisition of freetext pathology reports from scanned images through OCR software. However, issues emerge when considering the extraction of cancer notification items.

Automatic de-identification of electronic health records : an Australian perspective

We present an approach to automatically de-identify health records. In our approach, personal health information is identified using a Conditional Random Fields machine learning classifier, a large set of linguistic and lexical features, and pattern matching techniques. Identified personal information is then removed from the reports. The de-identification of personal health information is fundamental for the sharing and secondary use of electronic health records, for example for data mining and disease monitoring. The effectiveness of our approach is first evaluated on the 2007 i2b2 Shared Task dataset, a widely adopted dataset for evaluating de-identification techniques. Subsequently, we investigate the robustness of the approach to limited training data; we study its effectiveness on different type and quality of data by evaluating the approach on scanned pathology reports from an Australian institution. This data contains optical character recognition errors, as well as linguistic conventions that differ from those contained in the i2b2 dataset, for example different date formats. The findings suggest that our approach compares to the best approach from the 2007 i2b2 Shared Task; in addition, the approach is found to be robust to variations of training size, data type and quality in presence of sufficient training data.

De-Identification of health records using Anonym: Effectiveness and robustness across datasets

Objective Evaluate the effectiveness and robustness of Anonym, a tool for de-identifying free-text health records based on conditional random fields classifiers informed by linguistic and lexical features, as well as features extracted by pattern matching techniques. De-identification of personal health information in electronic health records is essential for the sharing and secondary usage of clinical data. De-identification tools that adapt to different sources of clinical data are attractive as they would require minimal intervention to guarantee high effectiveness. Methods and Materials The effectiveness and robustness of Anonym are evaluated across multiple datasets, including the widely adopted Integrating Biology and the Bedside (i2b2) dataset, used for evaluation in a de-identification challenge. The datasets used here vary in type of health records, source of data, and their quality, with one of the datasets containing optical character recognition errors. Results Anonym identifies and removes up to 96.6% of personal health identifiers (recall) with a precision of up to 98.2% on the i2b2 dataset, outperforming the best system proposed in the i2b2 challenge. The effectiveness of Anonym across datasets is found to depend on the amount of information available for training. Conclusion Findings show that Anonym compares to the best approach from the 2006 i2b2 shared task. It is easy to retrain Anonym with new datasets; if retrained, the system is robust to variations of training size, data type and quality in presence of sufficient training data.

Multi-action recognition via stochastic modelling of optical flow and gradients

In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.

Diversity of accuracy profiles for absolute pitch recognition

Most advanced musicians are able to identify and label a heard pitch if given an opportunity to compare it to a known reference note. This is called ‘relative pitch’ (RP). A much rarer skill is the ability to identify and label a heard pitch without the need for a reference. This is colloquially referred to as ‘perfect pitch’, but appears in the academic literature as ‘absolute pitch’ (AP). AP is considered by many as a remarkable skill. As people do not seem able to develop it intentionally, it is generally regarded as innate. It is often seen as a unitary skill and that a set of identifiable criteria can distinguish those who possess the skill from those who do not. However, few studies have interrogated these notions. The present study developed and applied an interactive computer program to map pitch-labelling responses to various tonal stimuli without a known reference tone available to participants. This approach enabled the identification of the elements of sound that impacted on AP. Pitch-labelling responses of 14 participants with AP were recorded for their accuracy. Each participant’s response to the stimuli was unique. Their accuracy of labelling varied across dimensions such as timbre, range and tonality. The diversity of performance between individuals appeared to reflect their personal musical experience histories.

Automatic tracking, super-resolution and recognition of human faces from surveillance video

Identifying an individual from surveillance video is a difficult, time consuming and labour intensive process. The proposed system aims to streamline this process by filtering out unwanted scenes and enhancing an individual's face through super-resolution. An automatic face recognition system is then used to identify the subject or present the human operator with likely matches from a database. A person tracker is used to speed up the subject detection and super-resolution process by tracking moving subjects and cropping a region of interest around the subject's face to reduce the number and size of the image frames to be super-resolved respectively. In this paper, experiments have been conducted to demonstrate how the optical flow super-resolution method used improves surveillance imagery for visual inspection as well as automatic face recognition on an Eigenface and Elastic Bunch Graph Matching system. The optical flow based method has also been benchmarked against the ``hallucination'' algorithm, interpolation methods and the original low-resolution images. Results show that both super-resolution algorithms improved recognition rates significantly. Although the hallucination method resulted in slightly higher recognition rates, the optical flow method produced less artifacts and more visually correct images suitable for human consumption.

Super-resolved faces for improved face recognition from surveillance video advances in biometrics

Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for computers and human operators to identify individuals from these videos. To overcome this problem, super-resolution can be used in conjunction with an automated face recognition system to enhance the spatial resolution of video frames containing the subject and narrow down the number of manual verifications performed by the human operator by presenting a list of most likely candidates from the database. As the super-resolution reconstruction process is ill-posed, visual artifacts are often generated as a result. These artifacts can be visually distracting to humans and/or affect machine recognition algorithms. While it is intuitive that higher resolution should lead to improved recognition accuracy, the effects of super-resolution and such artifacts on face recognition performance have not been systematically studied. This paper aims to address this gap while illustrating that super-resolution allows more accurate identification of individuals from low-resolution surveillance footage. The proposed optical flow-based super-resolution method is benchmarked against Baker et al.’s hallucination and Schultz et al.’s super-resolution techniques on images from the Terrascope and XM2VTS databases. Ground truth and interpolated images were also tested to provide a baseline for comparison. Results show that a suitable super-resolution system can improve the discriminability of surveillance video and enhance face recognition accuracy. The experiments also show that Schultz et al.’s method fails when dealing surveillance footage due to its assumption of rigid objects in the scene. The hallucination and optical flow-based methods performed comparably, with the optical flow-based method producing less visually distracting artifacts that interfered with human recognition.

Automated recognition of drunk driving on highways from video sequences

A new method for the detection of abnormal vehicle trajectories is proposed. It couples optical flow extraction of vehicle velocities with a neural network classifier. Abnormal trajectories are indicative of drunk or sleepy drivers. A single feature of the vehicle, eg., a tail light, is isolated and the optical flow computed only around this feature rather than at each pixel in the image.

A survey of tagging techniques for music, speech and environmental sound

Sound tagging has been studied for years. Among all sound types, music, speech, and environmental sound are three hottest research areas. This survey aims to provide an overview about the state-of-the-art development in these areas.We discuss about the meaning of tagging in different sound areas at the beginning of the journey. Some examples of sound tagging applications are introduced in order to illustrate the significance of this research. Typical tagging techniques include manual, automatic, and semi-automatic approaches.After reviewing work in music, speech and environmental sound tagging, we compare them and state the research progress to date. Research gaps are identified for each research area and the common features and discriminations between three areas are discovered as well. Published datasets, tools used by researchers, and evaluation measures frequently applied in the analysis are listed. In the end, we summarise the worldwide distribution of countries dedicated to sound tagging research for years.

Inpatient facial expression recognition with SMS alert

Facial expression recognition (FER) has been dramatically developed in recent years, thanks to the advancements in related fields, especially machine learning, image processing and human recognition. Accordingly, the impact and potential usage of automatic FER have been growing in a wide range of applications, including human-computer interaction, robot control and driver state surveillance. However, to date, robust recognition of facial expressions from images and videos is still a challenging task due to the difficulty in accurately extracting the useful emotional features. These features are often represented in different forms, such as static, dynamic, point-based geometric or region-based appearance. Facial movement features, which include feature position and shape changes, are generally caused by the movements of facial elements and muscles during the course of emotional expression. The facial elements, especially key elements, will constantly change their positions when subjects are expressing emotions. As a consequence, the same feature in different images usually has different positions. In some cases, the shape of the feature may also be distorted due to the subtle facial muscle movements. Therefore, for any feature representing a certain emotion, the geometric-based position and appearance-based shape normally changes from one image to another image in image databases, as well as in videos. This kind of movement features represents a rich pool of both static and dynamic characteristics of expressions, which playa critical role for FER. The vast majority of the past work on FER does not take the dynamics of facial expressions into account. Some efforts have been made on capturing and utilizing facial movement features, and almost all of them are static based. These efforts try to adopt either geometric features of the tracked facial points, or appearance difference between holistic facial regions in consequent frames or texture and motion changes in loca- facial regions. Although achieved promising results, these approaches often require accurate location and tracking of facial points, which remains problematic.