A Low-Light Sensor Image Enhancement Algorithm Based on HSI Color Model

Ma, Shiping; Ma, Hua; Xu, Yuelei; Li, Shuai; Lv, Chao; Zhu, Ming

doi:10.3390/s18103583

Cited by 28 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, illumination-processing of image based on deep learning has made favorable achievements. Ma et al [ 49 ] use deep convolutional neural network and HSI color space to enhance low-light image. Ma et al [ 9 ] first use Generative Adversarial Nets to process illumination of facial image.…”

Section: Related Workmentioning

confidence: 99%

A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps

Ling

Lin

et al. 2020

Sensors

View full text Add to dashboard Cite

In recent years, Generative Adversarial Networks (GANs)-based illumination processing of facial images has made favorable achievements. However, some GANs-based illumination-processing methods only pay attention to the image quality and neglect the recognition accuracy, whereas others only crop partial face area and ignore the challenges to synthesize photographic face, background and hair when the original face image is under extreme illumination (Image under extreme illumination (extreme illumination conditions) means that we cannot see the texture and structure information clearly and most pixel values tend to 0 or 255.). Moreover, the recognition accuracy is low when the faces are under extreme illumination conditions. For these reasons, we present an elaborately designed architecture based on convolutional neural network and GANs for processing the illumination of facial image. We use ResBlock at the down-sampling stage in our encoder and adopt skip connections in our generator. This special design together with our loss can enhance the ability to preserve identity and generate high-quality images. Moreover, we use different convolutional layers of a pre-trained feature network to extract varisized feature maps, and then use these feature maps to compute loss, which is named multi-stage feature maps (MSFM) loss. For the sake of fairly evaluating our method against state-of-the-art models, we use four metrics to estimate the performance of illumination-processing algorithms. A variety of experimental data indicate that our method is superior to the previous models under various illumination challenges in illumination processing. We conduct qualitative and quantitative experiments on two datasets, and the experimental data indicate that our scheme obviously surpasses the state-of-the-art algorithms in image quality and identification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps

Ling

Lin

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…When the ratio of the three components changes, the image will have color distortion. The HSI color space uses Hue (H), Saturation (S) and Intensity (I) to describe color images, which is compatible with the human visual system [17]. The HSI color space model is shown in Figure 4.…”

Section: Research and Establishment Of Imaging Model Ahsi Colormentioning

confidence: 99%

An Improved LWD Azimuth Gamma Imaging Model Based on HSI Space

Zhang

Lü³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In recent years, in the process of oil and gas exploration and development, the situation of drilling tools drilling out of the reservoir often occurs. Due to the lack of directional indication, the traditional LWD(Logging While Drilling) natural gamma measurement technology cannot guide drilling tools to return to the reservoir efficiently.In order to solve this problem, this paper improves the traditional radiometric gamma measurement technology and establishes a set of azimuth gamma imaging model. Firstly, the basic imaging model is established based on HSI (Hue, Saturation, Intensity) color space.Then, the study focuses on the design of the gamma data quality control algorithm, which can effectively suppress the original gamma data noise.In addition, the cubic spline interpolation algorithm is selected to support the model to obtain 360° omni-directional gamma data.Finally, the image processing technology based on fast grayscale grouping is applied in this study, which greatly improves the imaging effect.Field application shows that the model runs stably on site, and the azimuth gamma image is well indicative. It can monitor the relative position relationship between the borehole trajectory and the formation, which effectively improves the reservoir encounter rate, and has high application and promotion value.

show abstract

“…The algorithm in [9] possesses practical application value in the digital reconstruction of artworks. A deep convolutional neural network (CNN) model to enhance lowlight sensor images based on the HSI color space model was proposed in [10], and the experimental results show that the proposed algorithm significantly enhanced the brightness and contrast of the image and avoided color distortion and over enhancement.…”

Section: Introductionmentioning

confidence: 99%

An FPGA-Based Simple RGB-HSI Space Conversion Algorithm for Hardware Image Processing

et al. 2020

View full text Add to dashboard Cite

In this paper, a new, low-complexity, easy-to-implement hardware method for color space conversion between the red-green-blue (RGB) and the hue-saturation-intensity (HSI) color spaces called the simple RGB-HSI space conversion (S-SC) algorithm is proposed, which aims to provide more rapid computing due to the need for fewer operations. In the S-SC algorithm, we reconstruct the model of space conversion between the RGB color space and the HSI color space (RGB-HSI) by inverting the conversion from the HSI color space to the RGB color space of the traditional geometric derivation algorithm. As a result, the nonlinear model-realized RGB-HSI color space conversion by the geometric derivation algorithm is transformed into a linear conversion model, which can avoid complicated calculations such as trigonometric and inverse trigonometric functions in the color space conversion process. The model can effectively reduce the computational complexity of the algorithm and facilitate hardware implementation at the same time. To evaluate the performance of the S-SC algorithm, we first compare the S-SC algorithm with the geometric derivation algorithm from the computational complexity perspective. On this basis, we compare the S-SC algorithm with five other RGB-HSI color space conversion algorithms from the perspectives of error and conversion effect. Finally, we use the field programmable gate array (FPGA) hardware platform to analyze and verify the timing sequence and logical resource consumption and verify the effectiveness of the proposed algorithm with experimental results. We show that the S-SC algorithm achieves good performance in terms of conversion accuracy, logical unit resource occupancy, and output timing.

show abstract

A Low-Light Sensor Image Enhancement Algorithm Based on HSI Color Model

Cited by 28 publications

References 30 publications

A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps

A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps

An Improved LWD Azimuth Gamma Imaging Model Based on HSI Space

An FPGA-Based Simple RGB-HSI Space Conversion Algorithm for Hardware Image Processing

Contact Info

Product

Resources

About