Image Sharpening Research Articles

Underwater Image Enhancement Based on Local Contrast Correction and Multi-Scale Fusion

In this study, an underwater image enhancement method based on local contrast correction (LCC) and multi-scale fusion is proposed to resolve low contrast and color distortion of underwater images. First, the original image is compensated using the red channel, and the compensated image is processed with a white balance. Second, LCC and image sharpening are carried out to generate two different image versions. Finally, the local contrast corrected images are fused with sharpened images by the multi-scale fusion method. The results show that the proposed method can be applied to water degradation images in different environments without resorting to an image formation model. It can effectively solve color distortion, low contrast, and unobvious details of underwater images.

LR-cGAN: Latent representation based conditional generative adversarial network for multi-modality MRI synthesis

ObjectiveThis work aims to synthesize a real-like missing MRI modality using multiple modalities those already obtained, thus providing more abundant diagnostic information, and promoting the improvement of some downstream tasks, such as segmentation and diagnosis. MethodsWith an adversarial network modelling the nonlinear mapping between the inputs and the output, our proposed LR-cGAN extracts the inherent latent representations from different MRI modalities with N collaboratively trained encoders, and fuses them by a latent space processing network (LSPN) composed of several residual blocks. Apart from L1 loss, the image gradient difference loss (GDL) is considered additionally as the objective function to alleviate the problem of insufficient image sharpening. To validate the effectiveness of LR-cGAN, corresponding experiments were evaluated by peak SNR (PSNR), structural similarity index (SSIM) and normalized root-mean-square error (NRMSE) on BRATS 2015 dataset. ResultsCompared to single-modality input, two-modality input improves the synthesis results by 1.196 dB PSNR, 0.019 SSIM and 0.04 NRMSE. With more inputs added, the synthesis performance exhibits an increasing trend. Once any key component, that is, LSPN, GDL loss or adversarial loss, is removed, the quality of the results will reduce to a lower level, proving their contributions to our model. Meanwhile, the final performance of our LR-cGAN network outperforms REPLICA, M-GAN, MILR and sGAN in all metrics on different synthesis tasks, demonstrating its superiority. ConclusionOur proposed LR-cGAN has the flexible ability of receiving multiple modalities and generating realistic images compared to real modality images, having the potential to supplement diagnostic information in clinical.

Transfer Learning approach for grading of Diabetic Retinopathy

There has been a wide interest in applying Deep Learning (DL) algorithms for automated binary and multi class classification of colour fundus images affected with Diabetic Retinopathy (DR). These algorithms have shown high sensitivity and specificity for detecting DR in non-clinical setup. Transfer learning has been successfully tested in many medical imaging applications like skin cancer detection, pulmonary nodule detection, Alzheimer’s disease etc. This paper experiments with the different DL architectures such as VGG19, InceptionV3, ResNet50, MobileNet and NASNet for automated DR classification (binary and multi class) on Messidor dataset. The dataset is publicly available, and comprises of 1200 retinal fundus images. The images belong to four different classes of DR namely, normal (class 0), mild (class 1), moderate (class 2) and severe (class 3), graded based on the severity level of DR. In our experiment, we have enhanced the quality of input images by applying algorithms like CLAHE (Contrast Limited Adaptive Histogram Equalisation) algorithm and Powerlaw transformation as pre-processing techniques, which work on the small image patches with high accuracy, contrast limiting and image sharpening. Hyper parameter tuning on pretrained InceptionV3 architecture, resulted in enhancing the accuracy of the model. Both binary and multi class results were analysed considering inter class (one class with another class) accuracies. We achieved an accuracy of 78% between class 0 and class 1, the accuracy between class 0 and class 2 further reduced to 69%, while class 1 and class 2 showed an accuracy of 61%. Moreover, the interclass class accuracy between class 1 and class 3 was 62%, class 2 and class 3 further reduced to 49%. The accuracy further diminished between class 0 and class 3 to 32%. These experiments suggest that the pretrained models provided better results in classifying normal and mild, but they were not that much efficient in classifying moderate-severe and normal-severe binary classifications.

Machine vision based online detection of PCB defect

The traditional PCB defect on-line detection has the problems of long detection time and poor accuracy of detection results. Therefore, a key technology of PCB defect online detection based on machine vision is proposed. Firstly, image retrieval is carried out by using visual detection algorithm, image smoothing, image contrast enhancement, image sharpening and other preprocessing operations are carried out by using gray-scale transformation algorithm to simplify the operation process and improve the image quality; secondly, PC is analyzed B. the causes and types of defects. The original color image is processed and binarized by the hybrid recognition method of mathematical morphology and pattern recognition. Then the reference image obtained by mathematical morphology method is used as a template for system self inspection. Finally, the image aberration detection algorithm is introduced to segment the threshold value of PCB defect image, remove redundant points and mark PCB image defect recognition results, improve the visual detection algorithm and optimize the hardware design to achieve PCB image defect detection and recognition. The experimental results show that the method has high detection accuracy and short detection time, and can effectively control the stable operation of the online detection system, which provides a reference for related research in this field.

Research on blurred edge information segmentation of image based on computer vision

In the process of image fuzzy edge information segmentation by traditional methods, the segmentation effect is not ideal, the completion time is long and the accuracy is low. A fuzzy edge information segmentation method based on computer vision is proposed. After image denoising, image sharpening is carried out to extract image fuzzy edge information features. By designing a super-pixel grid, the pixels of the fuzzy edge information features of the image are matched, the inverse tensor information of the fuzzy edge of the image is analysed, and the multi-threshold values are normalised. The processing results are overlaid on the single object in the image to realise the fuzzy edge information segmentation. Experimental results show that the proposed method has better segmentation effect, shorter completion time and higher accuracy, and is of practical significance.

DeBAM: Decoder-Based Approximate Multiplier for Low Power Applications

Approximate computing is a promising method for designing power-efficient computing systems. Many image and compression algorithms are inherently error-tolerant and can allow errors up to a specific limit. In such algorithms, savings in power can be achieved by approximating the data path units, such as a multiplier. This letter presents a novel decoder logic-based multiplier design with the intent to reduce the partial products generated. Thus, leading to a reduction in the hardware complexity and power consumption while maintaining a low error rate. Our proposed design in an 8-bit format which achieves 40.96% and 22.30% power reduction compared to the accurate and approximate multipliers. Comprehensive simulations are carried out on image sharpening and compression algorithms to prove that the proposed design obtains a better quality-effort tradeoff than the existing multipliers.

Design of Atangana–Baleanu–Caputo fractional-order digital filter

Atangana–Baleanu–Caputo (ABC) fractional differential operator based upon Mittag-Leffler kernel exhibits all the advantages of conventional Riemann–Liouville and Caputo fractional differential operators; in addition, the kernel associated is non-singular. Therefore, this paper puts forward a closed-form analytical formulation for the design of an ABC-based fractional-order FIR filter for various signal processing and filtering applications. The closed-form expression is derived by utilizing backward finite difference method and fractional sample delay interpolation techniques. Furthermore, several design examples are considered to illustrate the effectiveness of the proposed method. From the analytical and simulation studies done, it is observed that the proposed design efficiently approximates the ideal frequency response of ABC-fractional differential operator. Finally, one-dimensional and two-dimensional applications of the proposed method are validated and compared against state-of-the-art methods for electrocardiogram (ECG) R-peak detection as well as for digital image sharpening.

Inverse-Scaled Lanczos Filtering for Image Sharpening

The edge response in retinal image is the first step for human vision recognizing the outside world. A variety of receptive field models for describing the impulse response have been proposed. Which satisfies the uncertain principle? occupied the interest from a point of minimizing the product (Δx)(Δ w) both in spatial and spectral. Among the typical edge response models, finally Gabor function and 2nd. Gaussian Derivative GD2 remained as strong candidates. While famous D. Marr and R. Young support GD2, many vision researchers prefer Gabor. The retinal edge response model is used for image sharpening.<br/> Different from the conventional image sharpening filters, this paper proposes a novel image sharpening filter by modifying the Lanczos resampling filter. The Lanczos filter is used for image scaling to resize digital images. Usually it works to interpolate the discrete sampled points like as a kind of smoothing filter not as sharpening. The Lanczos kernel is given by the product of sampling Sinc function and the scaled Sinc function. The scaled Sinc function expanded by the scale "s" plays a role of window function. The author noticed that the inverse scaling of Lanczos window can be used not for smoothing but for sharpening filter.<br/> This paper demonstrates how the proposed model works effectively in comparison with Gabor and GD2.

Reversible Data Hiding with Contrast Enhancement Based on Laplacian Image Sharpening

In 2014, Wu et al. proposed a reversible data hiding method with contrast enhancement (RDH-CE) that emphasized that the visual quality of the image was more important than having a high peak signal-to-noise ratio (PSNR). But this method focused only on global enhancements and ignored the details. There were more obvious distortions of the visual image as the embedding level increased, and embedding capacity was relatively low when the embedding level was small. Therefore, in this paper, we proposed a new RDH method with contrast enhancement based on Laplacian sharpening. First, the details of the edges of images and the clarity of images were emphasized by Laplacian sharpening, and the visual distortions of the images were reduced by sharpening scale factor. Then, the embedding capacity was increased by combining the difference expansion and digital inverse transformation to apply the operator to all of the pixels in the image. The experimental results demonstrate the effectiveness of the proposed scheme.

A hybrid algorithm for underwater image restoration based on color correction and image sharpening

In this paper, an effective method is proposed for restoring underwater image based on color correction and image sharpening. The main purpose of this method is to improve the visibility of underwater images. Traditional methods generally adopt color balancing method to restore the images. However, we found that color balancing has a poor effectiveness on underwater image when the values of blue channel are greater than other two channels, specially, red channel is great of small than blue channel. Therefore, we propose a hybrid method for color correction process based on a principle that exploits the relationship of three channels (red channel, green channel, and blue channel). On the other words, color balancing will be employed to restore the images when the values of red channel approximate to blue channel, while the DCP-base method will be used if otherwise. To enhance the sharpness of underwater image, we employed a sharpening process based on Maximum a Posteriori (MAP) method when color correction has finished. The proposed method also been validated through carrying out experiments on several underwater image datasets which are provided by previous researchers. Our validation has proved that the proposed method has a better performance than the state-of-the-art methods.

EM-Sign: A Non-Contact Recognition Method Based on 24 GHz Doppler Radar for Continuous Signs and Dialogues

We studied continuous sign language recognition using Doppler radar sensors. Four signs in Chinese sign language and American sign language were captured and extracted by complex empirical mode decomposition (CEMD) to obtain spectrograms. Image sharpening was used to enhance the micro-Doppler signatures of the signs. To classify the different signs, we utilized an improved Yolov3-tiny network by replacing the framework with ResNet and fine-tuned the network in advance. This method can remove the epentheses from the training process. Experimental results revealed that the proposed method can surpass the state-of-the-art sign language recognition methods in continuous sign recognition with a precision of 0.924, a recall of 0.993, an F1-measure of 0.957 and a mean average precision (mAP) of 0.99. In addition, dialogue recognition in three daily conversation scenarios was performed and evaluated. The average word error rate (WER) was 0.235, 10% lower than in of other works. Our work provides an alternative form of sign language recognition and a new approach to simplify the training process and achieve a better continuous sign language recognition effect.

Modeling and Rendering of Ocean Plane Visual Communication Scene Based on SLIP Model

Liu, A.Q., 2020. Modeling and rendering of ocean plane visual communication scene based on SLIP model. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 313-316. Coconut Creek (Florida), ISSN 0749-0208.With the continuous progress of earth observation, data processing and other technologies, 3d modeling and rendering of the sea surface have a vital impact on the visual reality of the application system. In some applications, the sea surface itself is the focus of visualization and the basic environment for other applications. The purpose of this paper is to realize the rapid and realistic rendering of the sea surface based on the wave model and grid generation. Based on the SLIP model, a new algorithm for image enhancement is proposed. The sea surface image was analyzed and studied, and the video image method based on SLIP model was proposed to achieve the purpose of video image sharpening, and the ocean surface effect communication modeling was established.

Image enhancement with lightness correction and image sharpening based on characteristics of vision for elderly persons

In general, as people age the functions of their sensory organs deteriorate. For example, in the eye of an elderly person, the visual field becomes dark owing to a decrease in the amount of light reaching the retina. Moreover, objects appear blurred due to a decrease in contrast sensitivity. In particular, the contrast sensitivity decreases remarkably as the spatial frequency increases. In this study, we propose an image enhancement method that considers the visual characteristics of elderly persons. The proposed method combines lightness correction and amplification of high spatial frequency components to obtain images with optimized visibility for elderly persons. In particular, lightness enhancement that guarantees color gamut via tone mapping is conducted. In addition, image sharpening is applied based on the inverse characteristic function of the contrast sensitivity curve. The experiments were performed using several digital color images to confirm the effectiveness of the proposed method.

A Review on Image Processing Techniques for Fisheries Application

Nowadays, the image processing technique has been used widely in the fields of science and technology. The use of the image processing technique is to improve the manual approach process to achieve accurate results. Since the manual approach shows, its time processing can be laborious to analyses extensive data and require a skilful researcher to experiment. The use of image processing technique can support to reduce several drawbacks. Therefore, many researchers prefer an alternative solution such as an automated or semiautomated system-based image to enhance the manual approach task. The image processing technology provides a variety of algorithms that modified according to the desired study is the reason why the image processing technique is desirable. Low-level processing is the early stage of image processing techniques and the steps involved are image acquisition, noise removal, image sharpening, image smoothing, image blurring, etc. Meanwhile for the Midlevel processing, adopt the use of several image processing techniques such as image segmentation, object detection, object recognition, feature extraction and classification. Therefore, image processing provides numerous applications such as in agriculture, medical image processing, ocean monitoring and conservation, facial recognition, fisheries, etc. In this paper, the uses of image processing techniques are discussed in briefly on the application of fishery study.

A NOVEL APPROACH FOR SHARPENING BLUR IMAGE USING CONVOLUTIONAL NEURAL NETWORKS

Image sharpening is done by passing blur picture as input and obtaining the sharp one at full resolution as output. The technique of sharpening blur image has more impact on different fields such as medical imaging, forensic science and astronomy. To enhance an image by using LSTM it takes more time complexity. In order to overcome those drawbacks we proposed CNN algorithm to get better performance by using ResBlocks. The proposed model addresses two general issues: the solver and relative arguments in every scale is same and different arguments in each scale cause instability. Another issue is the input image has different resolutions and different scales. In each scale parameter tweaking is allowed and over-fit is raised to the particular image. The proposed model takes sequence of blurry images in different resolutions and down sampled at encoder as-well-as convert the given input to the feature map then generates latent sharp image at every layer and provide the final sharp image at full resolution by converting back into the original format at decoder. Thus, it reduces the time complexity and gives the stable results.

A novel method based on convolutional neural network for malaria diagnosis

Malaria is one of the three major diseases with the highest mortality worldwide and can turn fatal if not taken seriously. The key to surviving this disease is its early diagnosis. However, manual diagnosis is time consuming and tedious due to the large amount of image data. Generally, computer-aided diagnosis can effectively improve doctors’ perception and accuracy. This paper presents a medical diagnosis method powered by convolutional neural network (CNN) to extract features from images and improve early detection of malaria. The image sharpening and histogram equalization method are used aiming at enlarging the difference between parasitized regions and other area. Dropout technology is employed in every convolutional layer to reduce overfitting in the network, which is proved to be effective. The proposed CNN model achieves a significant performance with the best classification accuracy of 99.98%. Moreover, this paper compares the proposed model with the pretrained CNNs and other traditional algorithms. The results indicate the proposed model can achieve state-of-the-art performance from multiple metrics. In general, the novelty of this work is the reduction of the CNN structure to only five layers, thereby greatly reducing the running time and the number of parameters, which is demonstrated in the experiments. Furthermore, the proposed model can assist clinicians to accurately diagnose the malaria disease.

Image Sharpening Detection Based on Difference Sets

Image sharpening is one of the basic operations used to improve the visual effect of images. Image editing makes it impossible to confirm the authenticity of an image, and the purpose of image forensics is to detect whether an image has been artificially edited. To solve this problem, a forensic algorithm based on global image pixel values is proposed. Twelve difference sets composed of first-order and second-order differences in different directions are used as the image feature to reveal the difference between image pixels. Additionally, the feature is used to determine whether the image has been sharpened or not. To verify the performance of the algorithm, a series of experiments are performed on different formats of image datasets. Compared with the existing forensic algorithms based on traditional machine learning, the detection accuracy of the proposed method is greatly improved.

On the Design of Logarithmic Multiplier Using Radix-4 Booth Encoding

This paper proposes an energy-efficient approximate multiplier which combines radix-4 Booth encoding and logarithmic product approximation. Additionally, a datapath pruning technique is proposed and studied to reduce the hardware complexity of the multiplier. Various experiments were conducted to evaluate the multiplier’s error performance and efficiency in terms of energy and area utilization. The reported results are based on simulations using TSMC-180nm. Also, the applicability of the proposed multiplier is examined in image sharpening and convolutional neural networks. The applicability assessment shows that the proposed multiplier can replace an exact multiplier and deliver up to a 75% reduction in energy consumption and up to a 50% reduction in area utilization. Comparative analysis with the state-of-the-art multipliers indicates the potential of the proposed approach as a novel design strategy for approximate multipliers. When compared to the state-of-the-art approximate non-logarithmic multipliers, the proposed multiplier offers smaller energy consumption with the same level of applicability in image processing and classification applications. On the other hand, some state-of-the-art approximate logarithmic multipliers exhibit lower energy consumption than the proposed multiplier but deliver significant performance degradation for the selected application cases.

FPGA-Based Multi-Level Approximate Multipliers for High-Performance Error-Resilient Applications

This paper presents approximate multipliers which are efficiently deployed on Field Programmable Gate Arrays (FPGAs) by using newly proposed approximate logic compressors at different levels of accuracy. Our approximate multiplier designs offer higher gains of power-delay-area products (PDAP) than those of the state-of-the-art works at comparable accuracies. Furthermore, in terms of delay, occupied area, and dynamic power dissipation, our designs are much better than Lookup Table based multiplier Intellectual Properties that are available on an FPGA. Particularly, our proposed 8-, 16-, and 32-bit multipliers can deliver PDAP gains up to 7.1 x, 8.3 x, and 5.0 x, respectively. The effectiveness and applicability of our designs are also demonstrated by image processing applications such as image multiplication and sharpening. The experiments show that for the image sharpening, our 8 x 8 multipliers can deliver a good peak signal-to-noise ratio (PSNR) of 46.81 dB, a structural similarity index metric (SSIM) of 0.9989, and a dynamic power saving of up to 36.7% with regard to the exact multiplier. For the image multiplication, approximate 16 x 16 multipliers can offer a high PSNR of 80.25 dB, an SSIM of 1.0, and a dynamic power saving of up to 58.15%. From these demonstrations, the proposed multipliers are expected to be appropriate with high-performance and low-power error-resilient applications.

Segmentation of Multi-Tumor from PET/CT Images

The aim of the project is to develop a methodology for automatic segmentation of multiple tumor from PET/CT images. Image pre-processing methods such as Contrast Limited Adaptive Histogram Equalization (CLAHE), image sharpening and Wiener filtering were performed to remove the artifacts due to contrast variations and noise. The image was segmented using K-means, Threshold segmentation, watershed segmentation, FCM clustering Segmentation, Mean shift Clustering Segmentation, Graph Cut Segmentation. Evaluation was made for the segmentation against the Ground Truth. Various Features was selected and extracted. Classification was made using SVM classifier and KNN classifier to classify the tumor as benign or malignant. The proposed method was carried out using PET/CT images of lung cancer patients and implemented using MATLAB.