44 results about "Reduced contrast volume" patented technology

Provided is a blood flow authentication ring that can achieve focus in a captured image regardless of finger size, can prevent reduction of contrast due to external light, or simplifies personal registration. A blood flow authentication ring in an embodiment of the present invention is a blood flow authentication ring having a ring-shaped cover member to be worn on a finger and configured to perform authentication with finger blood flow. The cover member at least includes an irradiation device to irradiate the finger with light and an imaging device to capture an image of light transmitted through the finger. An adjusting member is provided between an inner circumference of the cover member and the finger. The adjusting member has a function of at least one of a size compensation member and a low reflection member.

The invention relates to an underwater image restoration method based on multi-modal visual guidance and characteristic decomposition, which is used for solving the problems in the prior art that color distortion and contrast reduction of an image are caused by light absorption due to gradual attenuation of light with different wavelengths in water, and the light is scattered when encountering particles in the water, so that the image cannot be restored. And the problems of image blurring and detail loss are solved. According to the scheme, multi-mode prompt learning is adopted, complementarity among multiple modes is utilized, and features from different modes are integrated into prompt information so as to support color and contrast recovery of underwater images; and extracting high-frequency information from the RGB modal features by using learnable wavelets, and focusing on fine and difficult-to-perceive detail areas in the high-frequency features by using a high-frequency mixed attention module so as to recover the definition of textures in the underwater image.

The invention discloses an underwater image enhancement method and device based on multi-color space and frequency domain guidance, and the method comprises the steps: converting an inputted underwater image into three color spaces, namely RGB, HSV and LAB, based on a color extraction module in a multi-color space recovery sub-network, so as to carry out the color recovery of the image through the full utilization of the advantages of each color space; a color fusion module in the multi-color space recovery sub-network is used to adaptively correct color distortion of the underwater image by using a color attention mechanism; extracting, enhancing and fusing high and low frequency information of the image through a frequency domain enhancement sub-network; further enhancing the details and contrast of the image through a detail enhancement sub-network; and fusing the output feature maps of the three sub-networks, and finally outputting an enhanced underwater image. According to the method, the problems of color distortion, detail blurring and contrast reduction in the underwater image are effectively solved, and the color and texture details of the image can be truly restored.

Provided is a blood flow authentication ring that can achieve focus in a captured image regardless of finger size, can prevent reduction of contrast due to external light, or simplifies personal registration. A blood flow authentication ring in an embodiment of the present invention is a blood flow authentication ring having a ring-shaped cover member to be worn on a finger and configured to perform authentication with finger blood flow. The cover member at least includes an irradiation device to irradiate the finger with light and an imaging device to capture an image of light transmitted through the finger. An adjusting member is provided between an inner circumference of the cover member and the finger. The adjusting member has a function of at least one of a size compensation member and a low reflection member.

The invention discloses a medium-wave infrared illumination optical system design method, equipment and a storage medium, belongs to the technical field of infrared target simulation, and solves the technical problem that the diffraction efficiency and contrast are reduced when the prior art is applied to a medium-wave infrared illumination optical system. A DMD diffraction model is constructed, optical system analysis is carried out, the optimal pixel size and the optimal incidence pitch angle of the medium-wave infrared illumination optical system are obtained, and the medium-wave infrared illumination optical system comprises an illumination lens group, a shaping diaphragm, a trapezoidal prism, protection glass and a DMD target surface which are sequentially arranged along the light source emergent end. The light source converges light beams through the illumination lens group to form illumination light beams, the illumination light beams are shaped through the shaping diaphragm, and then the shaped illumination light beams are reflected to the target surface of the DMD through the trapezoidal prism. The medium-wave infrared illumination optical system is high in diffraction efficiency, small in stray light interference and capable of improving the contrast ratio of a projected image.

To appropriately reduce flicker caused by random noise in an analysis image used in failure analysis of a semiconductor device.SOLUTION: A learning method is a method for generating an inference model used to reduce flicker caused by random noise from an analysis image that is used in failure analysis of a semiconductor device. The method comprises: a learning acquisition step (S01) for acquiring an analysis image for learning including a target signal related to a semiconductor device and including random noise, and a noise image for learning including no target signal and including random noise; a noise addition step (S02, S03) of reducing the contrast of the analysis image for learning and adding random noise of the noise image for learning to the analysis image for learning with reduced contrast to generate a noise-added image for learning; and a training step (S04) in which machine learning of the inference model is trained using the noise-added image for learning.SELECTED DRAWING: Figure 6

The present invention provides a configuration for anti-counterfeiting printed material in which a first two-dimensional code, which is easily readable under visible light illumination and difficult to read under near-infrared light illumination, and a second two-dimensional code, which is difficult to read under visible light illumination and easily readable under near-infrared light illumination, are formed to overlap, thereby enabling easier reading of the two-dimensional codes than in conventional configurations. [Solution] A filter layer 9 that attenuates visible light and / or near-infrared light is formed in the overlapping area of ​​the first two-dimensional code 3 and the second two-dimensional code 4. With this configuration, when reading one of the two-dimensional codes 3 and 4, the contrast of the other two-dimensional code 3 and 4 that appears in the captured image is reduced, making it easier to read the two-dimensional codes 3 and 4 compared to the conventional configuration.

The invention provides an ultrasonic beam synthesis method based on deep learning, and belongs to the technical field of ultrasonic imaging, and the method comprises the steps: obtaining original echo signal data received by an ultrasonic probe, the original echo signal data comprising radio frequency data of a plurality of channels; processing the original echo signal data through a convolutional neural network model, extracting inter-channel feature correlation, and generating synthesized beam signal data; mapping the original echo signal data into a final ultrasonic imaging image based on a convolutional neural network model; and optimizing parameters of the convolutional neural network model through supervised training, wherein the supervised training adopts beam signal data generated by an advanced adaptive beam forming algorithm or a final ultrasonic imaging image as a label. According to the method, ultrasonic imaging can be realized through the convolutional neural network, the resolution and the contrast ratio of ultrasonic imaging can be remarkably improved for the business scene problems of complex multichannel radio frequency data processing, low feature extraction efficiency and limited image quality in traditional ultrasonic imaging, the calculation complexity is reduced, and the imaging quality is improved. A solution is provided for real-time high-quality imaging, and the method is suitable for scenes with high requirements for image quality and processing speed in medical diagnosis.

The application discloses a tunnel crack detection method based on image recognition and relates to the technical field of civil engineering structure health monitoring and operation and maintenance detection. The direction self-adaptive deblurring processing can significantly improve the integrity of the crack edge under the motion blur state, the slender crack still maintains clear morphological characteristics under the dynamic acquisition condition, and the crack breaking or missing detection problem caused by the blur is avoided; the illumination invariance feature enhancement mechanism is introduced to effectively overcome the interference of uneven illumination in the tunnel, the crack details in the shadow area and the overexposure area are fully reserved through dynamic balance of the brightness difference at the feature level, the contrast of the crack and the background is enhanced, and the false detection rate under the complex illumination condition is reduced; the collaborative design is adopted to guarantee the practicability and robustness of the system, the quality gate mechanism automatically filters the low-quality input, and invalid processing is avoided.

The application relates to a manufacturing method of myopia prevention control lenses and the myopia prevention control lenses, wherein the manufacturing method comprises the following steps: S1, pretreating a first curve of a lens body facing an eye; S2, coating a photoresist layer on the first curve; S3, covering a photo mask on the photoresist layer, and performing exposure treatment on the photoresist layer through light; and S4, washing and removing the photoresist layer through a developing solution to form a light diffusion zone. The myopia prevention control lens comprises a lens body, the lens body is provided with a first curve facing an eye and a second curve facing away from the eye; the first curve is provided with a clear vision zone and a light diffusion zone surrounding the clear vision zone, and the beneficial effect is that the clear vision zone effectively corrects vision, the light diffusion zone accurately realizes contrast reduction of different levels with high precision, the smoothness of the lens surface is higher, the projection effect of the lens on light is better, and the appearance is more beautiful.

Methods and systems for rendering watermarks may involve creating a digital watermark by applying grayscale inversion and contrast reduction to a document, thereby producing a visually distinguishable pattern, and rendering a digital watermark on a document in a manner that allows verification at different perspectives. A digital watermark may be created using a digital sample having a plurality of grayscale values. Based on the visibility and characteristics of the digital watermark, the document can be viewed from different angles to verify the validity of the document. The digital watermark may be modified based on predetermined parameters to facilitate enhanced fraud-proof security.

A contact lens (101) for preventing or slowing the progression or worsening of myopia, and methods of making and using the lens (101). The optical zone (102) of the lens includes a central region (105) having a base power. The optical zone (102) includes an annular region (103) circumferentially surrounding the central region (105). The annular region (103) includes a treatment zone (107) having a property that reduces the contrast of an image of an object formed by light passing through the central region (105) and the treatment zone as compared to an image of the object formed by light passing through only the central region (105). The property causing the reduction in contrast varies with meridians around the annular region (103). A peripheral zone (104) surrounding the annular region (103) has a constant thickness profile or a thickness variation configured to promote rotation of the lens (101) in each meridian.

The application discloses a manufacturing method of an LED chip and a mask set used for the LED chip, and reserves a measurement pattern area on an LED chip wafer; measurement patterns to be measured are transferred to the measurement pattern area to obtain an LED chip wafer finished product; the mask set used for the pattern transfer comprises a plurality of mask bodies; each mask body is provided with the same measurement pattern area; the measurement pattern area is provided with a measurement pattern; when the measurement pattern areas on the plurality of mask bodies are overlapped, the measurement patterns on each mask body are not overlapped with each other, different measurement patterns have a certain spacing, other lines are prevented from interfering, and based on the measurement pattern area, some film layers which are irrelevant to line width measurement and can cause contrast reduction can be selectively not plated through photolithography, so that the line width measurement value error caused by pattern stacking or film layer multiple contrast difference or no data is avoided, and subsequent AOI machine is facilitated to accurately measure the line width of the LED chip.

The application is an underwater image super-resolution reconstruction method based on dynamic window and state space cooperation. The method comprises a shallow feature extraction module, a deep feature extraction module and an image reconstruction module, through the construction of a double-path feature interaction mechanism, the alternative learning of a dynamic window attention module and a visual state space module is adopted, the cooperative optimization of local detail enhancement and global context modeling is realized. A dynamic channel gate feedforward network is innovatively designed, through a channel weight dynamic adjustment mechanism guided by a global average pooling, adaptive fusion of multi-scale features is realized. The method effectively solves the problems of blur and contrast reduction of underwater images caused by scattering effect, the PSNR is 28.21dB in the x3 task of the USR-248 dataset, which is 0.35dB higher than that of SRFormer, the experimental results show that the model has excellent performance in objective evaluation index and subjective evaluation, and remarkable effect is achieved in detail recovery, which has significant technical effect and industrial application value.

The invention relates to a method for reducing external stray light incident on an optical system (1), comprising the following steps: providing an optical system (1) in which imaging of a light source is ensured; positioning a transparent, plate-shaped light guide (3) in the optical system (1), wherein the light guide (3) has structural elements (6) on at least one of its large surfaces (3a, 3b) and / or within its volume, and each structural element (6) has at least one functional surface for the defined deflection of light, at which stray light is coupled into the light guide (3) and / or deflected from the optical axis, whereby stray light coupled into the light guide (3), if present, is coupled out again and / or absorbed at one or more surfaces of the light guide (3).such that at least 10% of the interfering light incident on the optical system (1) is coupled into the optical fiber (3) and thus removed from the optical path of the optical system (1), and such that the imaging of the light source is disturbed due to the limited scattering of the optical fiber (3) to such an extent that the Michelson contrast of the imaging of the optical system (1) is reduced by no more than a factor of 2. The invention further comprises an arrangement implementing the method and the use of the method or the arrangement in a head-up display.

A spectacle lens and to a method for producing such a lens, the spectacle lens comprising: a central main viewing region, with substantially constant optical power; an effect region around the central main viewing region, wherein the effect region has microstructures at least in part, said microstructures in the effect region bringing about an at least partially higher optical power than the optical power in the central main viewing region and / or at least partly a contrast reduction; and a peripheral region outside the effect region with a substantially constant optical power.

To eliminate a phenomenon that the light of the high luminance part of a video interferes with another dark part and the whole contrast is lowered in a stereoscopic screen in a dome shape or the like.SOLUTION: In a case where an image in which a bright portion and a dark portion are present is projected on a curved surface of a dome-shaped screen seen in a planetarium, an exhibition image, or the like or a projection screen disposed to face and be close to each other, the projection screens interfere with each other and the contrast is extremely lowered, but the screen of the present application has a three dimensional shape composed of a large number of planes, and thus mutual interference cannot physically occur. Therefore, even in the case of an image having a large difference between light and dark, a decrease in contrast in which the luminance of a bright portion interferes with a dark portion does not occur as in the case of a normal flat screen. Further, since a space is provided between the large number of planes, an acoustic problem such as reverberation occurring in a conventional dome screen or the like hardly occurs, and air conditioning is easily performed. In addition, the stereoscreen of the present application connected by the deformable member is foldable.SELECTED DRAWING: Figure 8

The present specification provides a method for providing information on angiography for contrast reduction performed by a processor, comprising the steps of: receiving a computed tomography angiography (CTA) projection image of an individual and said CTA contrast agent concentration data; selecting one of a first model for each contrast agent concentration that is trained to generate a first extracted image of a blood vessel using the projection image of the CTA as input based on said contrast agent concentration data; generating a first extracted image using the received projection image as input to the selected first model; and generating a rendering image from said first extracted image.

The application discloses a low-light enhancement method and device based on a dynamic filter and a storage medium, and belongs to the technical field of image processing. The low-light enhancement method based on the dynamic filter first extracts different scale features of an input low-light image by using a residual down-sampling module and a pyramid convolution pooling module in an encoder to obtain multi-scale image feature information; then, the feature information of different scales is input into a filter generation network to obtain each local dynamic filter at a decoding end, and the image feature information obtained by the encoder is input into a decoder to perform decoding processing by using each local dynamic filter and a pixel recombination up-sampling module, so that low-light enhancement and blur removal are realized. The method has the characteristics of multi-scale feature extraction, feature enhancement, spatial change adaptability and structure reservation, and solves the problem that insufficient light greatly reduces the visual quality of an image, and further causes image detail blur, contrast reduction and noise.

The application relates to a laser projection device and a laser projection system. A depolarizer component is additionally arranged on a laser display light path between a light source and a light modulation component, so that birefringence and interference effects occur in the depolarizer component, and polarized light is converted into random polarized light. Birefringence caused by lens stress in the light modulation component usually has a fixed fast and slow axis direction, which can affect the polarization state of light passing through the lens. In the embodiments provided by the application, the depolarizer component can rotate around the light beam propagation direction in the working state. When the light beam passes through the lens each time, the polarization direction of the light changes relative to the axis of the stress birefringence. The phase delay caused by the stress has different effects in different directions, and the effects are offset after time averaging, so that the negative influence of the birefringence effect caused by the lens stress on the depolarization effect of the depolarizer component can be reduced, and the speckle contrast can be greatly reduced, and the speckle suppression effect is improved.

This invention discloses a low-power display method, device, medium, and program product for medical images, relating to the field of image processing. The method includes: acquiring an initial medical image; performing identification processing on the initial medical image using a preset key diagnostic recognition model to determine key diagnostic areas in the initial medical image; based on the initial medical image, identifying areas outside the key diagnostic areas as non-key diagnostic areas; reducing the brightness and contrast of the non-key diagnostic areas to obtain a weakened image of the non-key diagnostic areas; generating an adjusted medical image based on the weakened images of the key and non-key diagnostic areas; and sending the adjusted medical image to a medical image display module. This invention, through the above method, can effectively reduce the power consumption of the display module while ensuring continuous high-definition display of medical images, achieving the goal of low-power display of medical images.

The embodiment of the invention provides a display panel and a display device. The display panel comprises a display substrate, a polarization layer and a barrier layer. The display substrate comprises at least one inorganic material layer. The polarization layer is located on one side of the display substrate and comprises a polarization function layer. The barrier layer is at least arranged between the inorganic material layer and the polarization function layer, and the barrier layer is configured to prevent the acid-base gas from diffusing to the polarization function layer. Acid-base gas generated by the inorganic material layer is prevented from permeating into the polarization function layer, so that the possibility of polarization function failure of the polarization function layer caused by contact between the polarization function layer and the acid-base gas can be reduced, the contrast ratio of the display panel is improved, the possibility of picture distortion of the display panel is reduced, and the display quality is improved. And the user experience is improved.

The invention discloses a display driving method and system and a display device, the display device comprises a display module and a backlight module, and the display driving method comprises the steps of decoding a video source signal and then outputting display data; after the display data is subjected to overdrive processing, a display control signal is output, and the display module is controlled to work according to the display control signal; and after the display data is subjected to over-drive processing, a backlight control signal is output, and the backlight module is controlled to work according to the backlight control signal. The problem that the instantaneous brightness and contrast ratio of the picture are reduced due to the fact that the current display picture has a trailing phenomenon and the light transmittance of the liquid crystal in the torsion process is in an intermediate state can be relieved.

Methods and systems for rendering a watermark, can involve creating a digital watermark by applying grayscale inversion and contrast reduction to a document, resulting in a visually distinguishable pattern and rendering a digital watermark on the document in a manner that allows verification at different viewing angles. The digital watermark can be created using a digital swatch sheet of multiple gray values. The document can be viewed varying angles to verify the validity of the document based on the visibility and characteristics of the digital watermark. The digital watermark may be modified on predetermined parameters to facilitate enhanced security against fraud.

The invention discloses a tunnel crack detection method based on image recognition, relates to the technical field of civil engineering structure health monitoring and operation and maintenance detection, and can remarkably improve the integrity of crack edges in a motion fuzzy state through direction self-adaptive deblurring processing. Clear morphological characteristics of the slender crack are still kept under the dynamic acquisition condition, and the problem of crack fracture or leak detection caused by fuzziness is avoided. An illumination invariance feature enhancement mechanism is introduced to effectively overcome the interference of uneven illumination in the tunnel, and the brightness difference is dynamically balanced on the feature level, so that crack details of a shadow area and an overexposure area are fully reserved, the contrast ratio of cracks and the background is enhanced, and the false detection rate under the complex illumination condition is reduced; collaborative design is adopted, the practicability and robustness of the system are guaranteed, a quality gating mechanism automatically filters low-quality input, and invalid processing is avoided.

The invention discloses an aero-engine part DR image enhancement method and device and a storage medium. According to the DR image enhancement method, firstly, a DR image to be enhanced is obtained, then, the ray scattering intensity of the DR image to be enhanced is calculated, then, the transmissivity of the DR image to be enhanced is calculated, a transmissivity algorithm is divided into a rough calculation part and a fine calculation part, and the fine calculation transmissivity can be obtained through guided filtering and regularization iterative calculation after rough calculation. After ray scattering intensity and fine calculation transmissivity are obtained, a picture with scattering noise removed can be obtained through calculation, finally gamma correction is conducted on the picture with scattering noise removed, and a final enhanced DR image is obtained. According to the method, the contrast ratio of the DR image is improved, the noise of the DR image is reduced, and the situation of missing detection of defects is avoided.

The embodiment of the invention provides an image display method and device, equipment and a storage medium. The method comprises the steps of determining a corresponding adaptive brightness mapping relation according to pixel brightness of a to-be-displayed image, the adaptive brightness mapping relation enables the difference value between the pixel brightness of the non-low-brightness pixel area of the to-be-displayed image after being displayed by the optical imaging system and the ideal brightness of the non-low-brightness pixel area not displayed by the optical imaging system to be smaller than a preset brightness difference value; according to the adaptive brightness mapping relation, the pixel brightness of the to-be-displayed image is converted, and the converted to-be-displayed image is displayed through the optical imaging system. According to the embodiment of the invention, the influence of reduction of the image quality caused by reduction of the in-eye contrast when the non-low-brightness pixel region of the to-be-displayed image is displayed through the optical imaging system can be eliminated, the to-be-displayed image is efficiently and clearly displayed through the optical imaging system, and the overall image quality after the image is displayed is improved.

The utility model discloses a double-DMD (Digital Micromirror Device) speckle-eliminating projection structure for improving laser projection color contrast, which comprises a light source device, a beam combining system, a dodging speckle-eliminating system, DMDs, a DMD time sequence control device and a projection output lens which are sequentially arranged along the light propagation direction, and a piezoelectric vibration table for applying vibration to the DMDs is also arranged on the DMDs; the light source device is used for emitting laser in various colors to the beam combining system; the beam combining system is used for spatially combining the lasers with multiple colors to form a single light beam; and the light uniformizing and spot eliminating system is used for enabling the combined light beams to output a light field with uniform intensity. The two DMDs are adopted for simultaneous control, so that the problem that the contrast ratio is reduced due to the fact that a single DMD is not turned over in time can be avoided; the piezoelectric vibration table can randomly change the optical path of the output image, so that different speckle patterns are formed on the screen, the speckle patterns of each frame are different, and the speckle contrast ratio is reduced by using the average effect of human eyes.

A remote method of performing the procedure of restoring fusion stability in patients with amblyopia, wherein a healthcare worker enters patient data obtained as a result of a preliminary examination and monitors performance of the procedure by the patient; based on the entered patient data, test objects are generated in a user interface on a patient's computer work station that are divided into parts, where some of the parts are red and some are green; while performing the procedure, the patient uses optical equipment consisting of red and blue photofilters; the patient, looking at a test object through the optical equipment, assembles the test object parts into a single image by means of an input device, where the test objects' contrast is reduced during performance of the procedure so that the better-seeing eye sees like the amblyopic eye.