scholarly journals An Efficient Compressive Convolutional Network for Unified Object Detection and Image Compression

2019 ◽  
Vol 33 ◽  
pp. 5949-5956 ◽  
Author(s):  
Xichuan Zhou ◽  
Lang Xu ◽  
Shujun Liu ◽  
Yingcheng Lin ◽  
Lei Zhang ◽  
...  
Keyword(s):  
Image Compression ◽  
Object Detection ◽  
Compressive Sensing ◽  
Sufficient Condition ◽  
Data Embedding ◽  
Convolutional Network ◽  
Convolution Operation ◽  
Computational Overhead ◽  
Convolution Kernels ◽  
Image Set

This paper addresses the challenge of designing efficient framework for real-time object detection and image compression. The proposed Compressive Convolutional Network (CCN) is basically a compressive-sensing-enabled convolutional neural network. Instead of designing different components for compressive sensing and object detection, the CCN optimizes and reuses the convolution operation for recoverable data embedding and image compression. Technically, the incoherence condition, which is the sufficient condition for recoverable data embedding, is incorporated in the first convolutional layer of the CCN model as regularization; Therefore, the CCN convolution kernels learned by training over the VOC and COCO image set can be used for data embedding and image compression. By reusing the convolution operation, no extra computational overhead is required for image compression. As a result, the CCN is 3.1 to 5.0 fold more efficient than the conventional approaches. In our experiments, the CCN achieved 78.1 mAP for object detection and 3.0 dB to 5.2 dB higher PSNR for image compression than the examined compressive sensing approaches.

scholarly journals Fast Transforms in Image Processing: Compression, Restoration, and Resampling

2014 ◽  
Vol 2014 ◽  
pp. 1-23 ◽  
Author(s):  
Leonid P. Yaroslavsky
Keyword(s):  
Image Processing ◽  
Image Compression ◽  
Image Restoration ◽  
Compressive Sensing ◽  
Adaptive Filters ◽  
Processing Methods ◽  
Fast Transforms ◽  
Image Transforms

Transform image processing methods are methods that work in domains of image transforms, such as Discrete Fourier, Discrete Cosine, Wavelet, and alike. They proved to be very efficient in image compression, in image restoration, in image resampling, and in geometrical transformations and can be traced back to early 1970s. The paper reviews these methods, with emphasis on their comparison and relationships, from the very first steps of transform image compression methods to adaptive and local adaptive filters for image restoration and up to “compressive sensing” methods that gained popularity in last few years. References are made to both first publications of the corresponding results and more recent and more easily available ones. The review has a tutorial character and purpose.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

Adaptive AFM imaging based on object detection using compressive sensing

Micron ◽  
2021 ◽  
pp. 103197
Author(s):  
Guoqiang Han ◽  
Yongjian Chen ◽  
Teng Wu ◽  
Huaidong Li ◽  
Jian Luo
Keyword(s):  
Object Detection ◽  
Compressive Sensing ◽  
Afm Imaging

Compression of Secondary Ion Microscopy Image Sets Using a Three-dimensional Wavelet Transformation

2000 ◽  
Vol 6 (1) ◽  
pp. 68-75 ◽  
Author(s):  
Martin G. Wolkenstein ◽  
Herbert Hutter
Keyword(s):  
Image Compression ◽  
Wavelet Transformation ◽  
Signal To Noise Ratio ◽  
Three Dimensional ◽  
Compression Method ◽  
Signal To Noise ◽  
Microscopy Image ◽  
Image Set ◽  
Ion Microscopy ◽  
Secondary Ion

This article proposes a lossy three-dimensional (3-D) image compression method for 3-D secondary ion microscopy (SIMS) image sets that uses a separable nonuniform 3-D wavelet transform. A typical 3-D SIMS measurement produces relatively large amounts of data which has to be reduced for archivation purposes. Although it is possible to compress an image set slice by slice, more efficient compression can be achieved by exploring the correlation between slices. Compared to different two-dimensional (2-D) image compression methods, compression ratios of the 3-D wavelet method are about four times higher at a comparable peak signal-to-noise ratio (PSNR).

Sign in / Sign up

Export Citation Format

Share Document