John C. Pearson

Video Quality Experts Group: Current Results and Future Directions

The Video Quality Experts Group (VQEG) was formed in October 1997 to address video quality issues. The group is composed of experts from various backgrounds and affiliations, including participants from several internationally recognized organizations working int he field of video quality assessment. The first task undertaken by VQEG was to provide a validation of objective video quality measurement methods leading to recommendations in both the telecommunications and radiocommunication sectors of the International Telecommunications Union. To this end, VQEG designed and executed a test program to compare subjective video quality evaluations to the predictions of a number of proposed objective measurement methods for video quality in the bit rate range of 768 kb/s to 50 Mb/s. The results of this test show that there is no objective measurement system that is currently able to replace subjective testing. Depending on the metric used for evaluation, the performance of eight or nine models was found to be statistically equivalent, leading to the conclusion that no single model outperforms the others in all cases. The greatest achievement of this first validation effort is the unique data set assembled to help future development of objective models.

Learning contextual relationships in mammograms using a hierarchical pyramid neural network

This paper describes a pattern recognition architecture, which we term hierarchical pyramid/neural network (HPNN), that learns to exploit image structure at multiple resolutions for detecting clinically significant features in digital/digitized mammograms. The HPNN architecture consists of a hierarchy of neural networks, each network receiving feature inputs at a given scale as well as features constructed by networks lower in the hierarchy. Networks are trained using a novel error function for the supervised learning of image search/detection tasks when the position of the objects to be found is uncertain or ill defined. We have evaluated the HPNNs ability to eliminate false positive (FP) regions of interest generated by the University of Chicagos Computer-aided diagnosis (CAD) systems for microcalcification and mass detection. Results show that the HPNN architecture, trained using the uncertain object position (UOP) error function, reduces the FP rate of a mammographic CAD system by approximately 50% without significant loss in sensitivity. Investigation into the types of FPs that the HPNN eliminates suggests that the pattern recognizer is automatically learning and exploiting contextual information. Clinical utility is demonstrated through the evaluation of an integrated system in a clinical reader study. We conclude that the HPNN architecture learns contextual relationships between features at multiple scales and integrates these features for detecting microcalcifications; and breast masses.

Integrating neural networks with image pyramids to learn target context

The utility of combining neural networks with pyramid representations for target detection in aerial imagery is explored. First, it is shown that a neural network constructed using relatively simple pyramid features is a more effective detector, in terms of its sensitivity, than a network which utilizes more complex object-tuned features. Next, an architecture that supports coarse-to-fine search, context learning and data fusion is tested. The accuracy of this architecture is comparable to a more computationally expensive non-hierarchical neural network architecture, and is more accurate than a comparable conventional approach using a Fisher discriminant. Contextual relationships derived both from low-resolution imagery and supplemental data can be learned and used to improve the accuracy of detection. Such neural network/pyramid target detectors should be useful components in both user assisted search and fully automatic target recognition and monitoring systems.

Multisensor integration in biological systems

The authors discuss the integration of sensory information in biological systems. In particular, they consider the structure in vertebrate animals that utilizes multiple sensory inputs to orient the sensor platform, i.e. the body or the head, toward objects of interest. This structure is known as the optic tectum in lower vertebrates and the superior colliculus in mammals. The representation of the various sensory modalities on the tectum follows the maplike image format of the retina. This requires in some cases a considerable transformation from the original representation of the sensory input available from the other sensors. As an example, the authors present a detailed discussion of the visual/acoustic object localization system of the barn owl along with a model for the adaptive coregistration of the coordinate systems of the visual and acoustic maps on the tectum.<<ETX>>

Accuracy and cross-calibration of video-quality metrics: new methods from ATIS/T1A1

Video quality metrics (VQM) have often been evaluated and compared using simple measures of correlation with observers. This approach does not fully take into account the variability implicit in the observers. We present techniques for determining the statistical resolving power of a VQM, defined as the minimum change in the value of the metric for which subjective test scores show a significant change. These techniques have been applied to the VQEG dataset, and incorporated into the recent ATIS/T1A1 series of technical reports (TR), which provide a comprehensive framework for characterizing and validating full-reference video quality metrics (VQM). These approved TR, while not standards, will enable the USA telecommunications industry to incorporate video quality metrics into contracts and tariffs for compressed video distribution. New methods for assessing VQM accuracy and cross-calibrating VQM are an integral part of the framework. These methods have been applied to two VQM at this point: PSNR and the version of Sarnoffs JNDmetrix tested by VQEG. The framework is readily extensible to additional VQM.

A hierarchical neural network architecture that learns target context: applications to digital mammography

An important problem in image analysis is finding small objects in large images. The problem is challenging because: 1) searching a large image is computationally expensive; and 2) small targets (on the order of a few pixels in size) have relatively few distinctive features which enable them to be distinguished from non-targets. To overcome these challenges the authors have developed a hierarchical neural network architecture which combines multiresolution pyramid processing with neural networks. Here the authors discuss the application of their hierarchical neural network architecture to the problem of detecting microcalcifications in digital mammograms. Microcalcifications are cues for breast tumors. 30% to 50% of breast carcinomas have microcalcifications visible in mammograms while 60% to 80% of all breast tumors eventually show microcalcifications via histology. Similar to the building/ATR problem, microcalcifications are generally very small point-like objects (<10 pixels in mammograms) which are hard to detect. Radiologists must often exploit other information in the imagery (e.g. location of blood vessels, ducts, etc.) in order to detect these microcalcifications. Here the authors examine how well their hierarchical neural network architecture learns and exploits contextual information in mammograms.

A neural network system for large- vocabulary continuous speech recognition in variable acoustic environments

Performance of speech recognizers is typically degraded by deleterious properties of the acoustic environment, such as multipath distortion (reverberation) and ambient noise. The degradation becomes more prominent as the microphone is positioned more distant from the speaker, for instance, in a teleconferencing application. Mismatched training and testing conditions, such as frequency response, microphone, signal-to-noise ratio (SNR), and room reverberation, also degrade recognition performance. Among available approaches to handling mismatches between training and testing conditions, a popular one is to retrain the speech recognizer under new environments. Hidden Markov models (HMM) have to date been accepted as an effective classification method for large vocabulary continuous speech recognition, e.g., the ARPA-sponsored SPHINX and DECIPHER. Retraining of HMM-based recognizers is a complex and tedious task. It requires recollection of speech data under corresponding conditions and reestimation of HMMs parameters. Particularly great time and effort are needed to retrain a recognizer which operates in a speaker-independent mode, which is the mode of greatest general interest.

Models of the Computation of Sound Elevation in the Barn Owl

We present a model of the first stage in the part of the barn owl’s auditory system which computes the elevation of a sound from the pressure levels at the ears. We also give a detailed description of our simulations of the model. Using several novel techniques, a few seconds of real time on a Sun Sparestation are sufficeint to simulate 2000 neurons for 100 milliseconds of simulated time. The response properties of the model neurons are a good match to those of real neurons.

Exploiting context in mammograms: a hierarchical neural network for detecting microcalcifications

Microcalcifications are important cues used by radiologists for early detection in breast cancer. Individually, microcalcifications are difficult to detect, and often contextual information (e.g. clustering, location relative to ducts) can be exploited to aid in their detection. We have developed an algorithm for constructing a hierarchical pyramid/neural network (HPNN) architecture to automatically learn context information for detection. To test the HPNN we first examined if the hierarchical architecture improves detection of individual microcalcifications and if context is in fact extracted by the network hierarchy. We compared the performance of our hierarchical architecture versus a single neural network receiving input from all resolutions of a feature pyramid. Receiver operator characteristic (ROC) analysis shows that the hierarchical architecture reduces false positives by a factor of two. We examined hidden units at various levels of the processing hierarchy and found what appears to be representations of ductal location. We next investigated the utility of the HPNN if integrated as part of a complete computer-aided diagnosis (CAD) system for microcalcification detection, such as that being developed at the University of Chicago. Using ROC analysis, we tested the HPNNs ability to eliminate false positive regions of interest generated by the computer, comparing its performance to the neural network currently used in the Chicago system. The HPNN achieves an area under the ROC curve of Az equal to .94 and a false positive fraction of FPF equal to .21 at TPF equals 1.0. This is in comparison to the results reported for the Chicago network; Az equal to .91, FPF equal to .43 at TPF equal to 1.0. These differences are statistically significant. We conclude that the HPNN algorithm is able to utilize contextual information for improving microcalcifications detection and potentially reduce the false positive rates in CAD systems.

Artificial neural networks as TV signal processors

Although color TV is an established technology, there are a number of long-standing problems for which neural networks may be suited. Impulse noise is such a problem, and a modular neural network approach is presented in this paper. The training and analysis was done on conventional computers, while real-time simulations were performed on a massively parallel computer, the Princeton Engine. The network approach was compared to a conventional alternative, a median filter, and real-time simulations and quantitative analysis demonstrated the technical superiority of the neural system. Ongoing work is investigating the complexity and cost of implementing this system in hardware.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.