Adaptive Dynamic Range Compression Research Articles

Effects of noise and reverberation on speech recognition with variants of a multichannel adaptive dynamic range compression scheme

Objective: Adaptive compression methods in hearing aids have been developed to maximise audibility while preserving temporal envelope modulations. Increasing the number of channels may improve listening comfort for loud sounds. However, the effects of this on speech recognition in different environmental conditions are unknown. This study evaluated the effects of different channel architectures and adaptive compression properties on speech recognition in noise and reverberation.Design: Sentences were mixed with steady or modulated noise at three signal-to-noise ratios (SNRs). These were processed with and without reverberation and amplified with four proprietary adaptive compression methods or linear amplification.Study sample: 36 listeners with mild to moderately-severe hearing loss.Results: Adaptive compression improved speech recognition over linear amplification to a small extent, with no significant differences among methods using 4 or 24 channels or a combination thereof. These effects remained across the different background noise and reverberation conditions.Conclusions: Increasing the number of channels does not negatively affect speech recognition in noise and reverberation when adaptive compression is used. If future research shows that increasing the number of channels improves listening comfort for loud sounds, these results indicate that adaptive compression methods with as many as 24 channels are viable options for hearing aids.

Real-time implementation of an adaptive simultaneous dynamic range compression and local contrast enhancement algorithm on a GPU

Dynamic range compression is a fundamental function required in digital video cameras and display monitors to improve the visual appeal of color images. This paper presents a real-time implementation of an algorithm for adaptive dynamic range compression and contrast enhancement on a graphics processing unit (GPU). To achieve this, we first designed an adaptive intensity transfer function to handle the enhancement of standard-dynamic-range (8 bits/channel) images with both low- and high-intensity. The proposed algorithm then combines the intensity transfer function with an existing simultaneous dynamic range compression and local contrast enhancement (SDRCLCE) algorithm for the simultaneous compression of dynamic range and enhancement of local contrast. To reach real-time performance in processing high-resolution color images, the proposed algorithm is implemented using an NVIDIA GeForce GTX 650 Ti GPU based on NVIDIA’s Compute Unified Device Architecture (CUDA) parallel programming running on a 3.33 GHz Intel Core i5-661 CPU. Compared with a LUT-accelerated implementation, the proposed GPU implementation was shown to accelerate the processing of 1024 × 1024 color images by 11.1 times and color images of 4096 × 4096 pixels by 7.5 times, including the cost of memory copy between the host and device.

Target recognitions in multiple-camera closed-circuit television using color constancy

People tracking in crowded scenes from closed-circuit television (CCTV) footage has been a popular and challenging task in computer vision. Due to the limited spatial resolution in the CCTV footage, the color of people’s dress may offer an alternative feature for their recognition and tracking. However, there are many factors, such as variable illumination conditions, viewing angles, and camera calibration, that may induce illusive modification of intrinsic color signatures of the target. Our objective is to recognize and track targets in multiple camera views using color as the detection feature, and to understand if a color constancy (CC) approach may help to reduce these color illusions due to illumination and camera artifacts and thereby improve target recognition performance. We have tested a number of CC algorithms using various color descriptors to assess the efficiency of target recognition from a real multicamera Imagery Library for Intelligent Detection Systems (i-LIDS) data set. Various classifiers have been used for target detection, and the figure of merit to assess the efficiency of target recognition is achieved through the area under the receiver operating characteristics (AUROC). We have proposed two modifications of luminance-based CC algorithms: one with a color transfer mechanism and the other using a pixel-wise sigmoid function for an adaptive dynamic range compression, a method termed enhanced luminance reflectance CC (ELRCC). We found that both algorithms improve the efficiency of target recognitions substantially better than that of the raw data without CC treatment, and in some cases the ELRCC improves target tracking by over 100% within the AUROC assessment metric. The performance of the ELRCC has been assessed over 10 selected targets from three different camera views of the i-LIDS footage, and the averaged target recognition efficiency over all these targets is found to be improved by about 54% in AUROC after the data are processed by the proposed ELRCC algorithm. This amount of improvement represents a reduction of probability of false alarm by about a factor of 5 at the probability of detection of 0.5. Our study concerns mainly the detection of colored targets; and issues for the recognition of white or gray targets will be addressed in a forthcoming study.

An adaptive dynamic range compression with local contrast enhancement algorithm for real-time color image enhancement

Dynamic range compression has become an important function used in modern digital video cameras to improve visual quality of color images suffered from low dynamic range and poor contrast defects. This study addresses real-time implementation of an adaptive dynamic range compression algorithm for color image/video enhancement. To achieve this purpose, we first propose a new image-dependent nonlinear intensity-transfer function to produce a satisfactory dynamic range compression result with less color artifacts. The proposed algorithm is then derived by combining the new adaptive nonlinear intensity-transfer function with an efficient local contrast enhancement algorithm. Moreover, an algorithmic acceleration method is also presented to accelerate the processing speed of the proposed color image enhancement method, achieving real-time performance in processing high-definition video signals. Experimental results validate the performance of the developed method in terms of quantitative evaluation, visual quality, computational efficiency, and power consumption.

Computerized image analysis: estimation of breast density on mammograms.

An automated image analysis tool is being developed for the estimation of mammographic breast density. This tool may be useful for risk estimation or for monitoring breast density change in prevention or intervention programs. In this preliminary study, a data set of 4-view mammograms from 65 patients was used to evaluate our approach. Breast density analysis was performed on the digitized mammograms in three stages. First, the breast region was segmented from the surrounding background by an automated breast boundary-tracking algorithm. Second, an adaptive dynamic range compression technique was applied to the breast image to reduce the range of the gray level distribution in the low frequency background and to enhance the differences in the characteristic features of the gray level histogram for breasts of different densities. Third, rule-based classification was used to classify the breast images into four classes according to the characteristic features of their gray level histogram. For each image, a gray level threshold was automatically determined to segment the dense tissue from the breast region. The area of segmented dense tissue as a percentage of the breast area was then estimated. To evaluate the performance of the algorithm, the computer segmentation results were compared to manual segmentation with interactive thresholding by five radiologists. A "true" percent dense area for each mammogram was obtained by averaging the manually segmented areas of the radiologists. We found that the histograms of 6% (8 CC and 8 MLO views) of the breast regions were misclassified by the computer, resulting in poor segmentation of the dense region. For the images with correct classification, the correlation between the computer-estimated percent dense area and the "truth" was 0.94 and 0.91, respectively, for CC and MLO views, with a mean bias of less than 2%. The mean biases of the five radiologists' visual estimates for the same images ranged from 0.1% to 11%. The results demonstrate the feasibility of estimating mammographic breast density using computer vision techniques and its potential to improve the accuracy and reproducibility of breast density estimation in comparison with the subjective visual assessment by radiologists.