Impact Of Image Compression Research Articles

Impact of Image Compression on In Vitro Cell Migration Analysis

Collective cell movement is an indication of phenomena such as wound healing, embryonic morphogenesis, cancer invasion, and metastasis. Wound healing is a complicated cellular and biochemical procedure in which skin cells migrate from the wound boundaries into the wound area to reconstruct the injured skin layer(s). In vitro analysis of cell migration is an effective assay for measuring changes in cell migratory complement in response to experimental inspections. Open-source segmentation software (e.g., an ImageJ plug-in) is available to analyze images of in vitro scratch wound healing assays; however, often, these tools are error-prone when applied to, e.g., low-contrast, out-of-focus, and noisy images, and require manual tuning of various parameters, which is imprecise, tedious, and time-consuming. We propose two algorithmic methods (namely log gradient segmentation and entropy filter segmentation) for cell segmentation and the subsequent measurement of the collective cell migration in the corresponding microscopic imagery. We further investigate the effects of image compression on the algorithms’ measurement accuracy, applying lossy compression algorithms (the current ISO standards JPEG2000, JPEG, JPEG-XL and AV1, BPG, and WEBP). We aim to identify the most suitable compression algorithm that can be used for this purpose, relating rate–distortion performance as measured in terms of peak signal-to-noise ratio (PSNR) and the multiscale structural similarity index (MS-SSIM) to the segmentation accuracy obtained by the segmentation algorithms. The experimental results show that the log gradient segmentationalgorithm provides robust performance for segmenting the wound area, whereas the entropy filter segmentation algorithm is unstable for this purpose under certain circumstances. Additionally, the best-suited compression strategy is observed to be dependent on (i) the segmentation algorithm used and (ii) the actual data sequence being processed.

Impact of Image Compression on the Performance of Steel Surface Defect Classification with a CNN

Machine vision is increasingly replacing manual steel surface inspection. The automatic inspection of steel surface defects makes it possible to ensure the quality of products in the steel industry with high accuracy. However, the optimization of inspection time presents a great challenge for the integration of machine vision in high-speed production lines. In this context, compressing the collected images before transmission is essential to save bandwidth and energy, and improve the latency of vision applications. The aim of this paper was to study the impact of quality degradation resulting from image compression on the classification performance of steel surface defects with a CNN. Image compression was applied to the Northeastern University (NEU) surface-defect database with various compression ratios. Three different models were trained and tested with these images to classify surface defects using three different approaches. The obtained results showed that trained and tested models on the same compression qualities maintained approximately the same classification performance for all used compression grades. In addition, the findings clearly indicated that the classification efficiency was affected when the training and test datasets were compressed using different parameters. This impact was more obvious when there was a large difference between these compression parameters, and for models that achieved very high accuracy. Finally, it was found that compression-based data augmentation significantly increased the classification precision to perfect scores (98–100%), and thus improved the generalization of models when tested on different compression qualities. The importance of this work lies in exploiting the obtained results to successfully integrate image compression into machine vision systems, and as appropriately as possible.

Impact of image compression on deep learning-based mammogram classification

Image compression is used in several clinical organizations to help address the overhead associated with medical imaging. These methods reduce file size by using a compact representation of the original image. This study aimed to analyze the impact of image compression on the performance of deep learning-based models in classifying mammograms as “malignant”—cases that lead to a cancer diagnosis and treatment—or “normal” and “benign,” non-malignant cases that do not require immediate medical intervention. In this retrospective study, 9111 unique mammograms–5672 normal, 1686 benign, and 1754 malignant cases were collected from the National Cancer Center in the Republic of Korea. Image compression was applied to mammograms with compression ratios (CRs) ranging from 15 to 11 K. Convolutional neural networks (CNNs) with three convolutional layers and three fully-connected layers were trained using these images to classify a mammogram as malignant or not malignant across a range of CRs using five-fold cross-validation. Models trained on images with maximum CRs of 5 K had an average area under the receiver operating characteristic curve (AUROC) of 0.87 and area under the precision-recall curve (AUPRC) of 0.75 across the five folds and compression ratios. For images compressed with CRs of 10 K and 11 K, model performance decreased (average 0.79 in AUROC and 0.49 in AUPRC). Upon generating saliency maps that visualize the areas each model views as significant for prediction, models trained on less compressed (CR < = 5 K) images had maps encapsulating a radiologist’s label, while models trained on images with higher amounts of compression had maps that missed the ground truth completely. In addition, base ResNet18 models pre-trained on ImageNet and trained using compressed mammograms did not show performance improvements over our CNN model, with AUROC and AUPRC values ranging from 0.77 to 0.87 and 0.52 to 0.71 respectively when trained and tested on images with maximum CRs of 5 K. This paper finds that while training models on images with increased the robustness of the models when tested on compressed data, moderate image compression did not substantially impact the classification performance of DL-based models.

The effect of image compression on synthetic PROBA-V images

We have carried out an in-depth investigation into the effects of image compression on synthetic Probe for On-Board Autonomy – Vegetation (PROBA-V) scenes and Landsat-derived image tiles. The two image compression implementations used were the TER implementation and a bespoke implementation of the Consultative Committee for Space Data Systems (CCSDS) Blue Book standard, which are functionally identical but operate on different image architectures. This work included (1) the development of an approach for producing synthetic scenes that were appropriate in terms of structure and content, and (2) evaluation of the image compression approach on the two kinds of image in terms of their usefulness for land-cover mapping. The synthetic image (SI) generation approach has been rigorously tested and produces images that are statistically similar to real scenes, both compressed and uncompressed. The results of our work show that the effects of image compression vary significantly between bands and with different compression ratios, and that the impact of image compression on image quality does vary with spatial scale. We also found indications of increased error rate at boundaries within the imagery. While the SI generation process and the processing chain of this imagery are not completely consistent with PROBA-V imagery, agreement was found among many of the results produced by the two approaches.

The impact of image compression on diagnostic quality of digital images for detection of chemically-induced periapical lesions.

To test the hypothesis that there is no significant difference in the detectability of chemically-induced periapical lesions between a non-compressed image and one subjected to a Joint Photographic Experts Group (JPEG) lossy compression technique at a ratio of 23:1 or less. Chemically-induced periapical lesions were created by placing a solution of 70% perchloric acid at the apex of extracted teeth in 13 human jaw cadaver specimens. Acid was applied in seven incremental time periods from 0-32 h. Extracted teeth were replaced in the socket and images were made using the Schick CDR digital sensor. Using a JPEG lossy compression algorithm, five compression ratios of 2:1, 14:1, 23:1, 28:1 and 47:1 were applied to the images. Images were viewed three times by three observers who ranked the presence or absence of a lesion at three sites, the mesial area, distal area and apex of the tooth, on a 5-point confidence scale. Intraobserver and interobserver agreement and agreement between the compressed and the original images were assessed with intraclass correlation coefficients (ICCs). Overall ICCs for measuring intraobserver agreement using all images were 0.77, 0.84, and 0.50 for the three observers, respectively. The overall ICC for assessing agreement between observers was 0.57. There was no significant difference (P>0.05) between compressed and original images for any site at compression ratios of 2:1, 23:1 and 28:1. There were significant differences for a compression ratio of 47:1. JPEG compression does not impact detectability of artificial periapical lesions at low and moderate compression ratios up to and including 28:1.