Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

76results about How to "Natural effect" patented technology

Finger print collecting and joining method supporting arbitrary directional rolling

The invention relates to a method for collecting and splicing a fingerprint, which can support the rolling in any direction and is a method for identifying and processing a fingerprint picture. The method applies a fingerprint collecting system which is composed of a fingerprint collector, a computer and a fingerprint collecting and splicing program, and comprises the steps of starting the initialization of the fingerprint collecting and splicing program, initial collecting, formal collecting, determining a fingerprint area of a current frame, updating a spliced picture, determining a fingerprint area of the spliced picture, generating a picture with splicing effects and displaying the picture with splicing effects. The method adopts a picture splicing method with a background picture as a reference and eliminates the restriction of the rolling direction during a fingerprint collecting process by rolling so that a complete fingerprint splicing picture can be formed with a finger to roll on a fingerprint collecting surface in any direction. In addition, the method also applies the weighted average method to process edges of the fingerprint splicing picture to ensure that the spliced fingerprint picture can be more natural and smooth.
Owner:北京海鑫科金高科技股份有限公司

Image processing method based on multi-camera, mobile terminal and storage medium

The present application is applicable to the field of image processing technology, and provides an image processing method based on multiple cameras, a mobile terminal and a computer readable storagemedium. The method comprises: obtaining the current preview picture collected by multiple cameras respectively, and determining whether the difference between the image parameters of the plurality ofpreview pictures conforms to a preset condition, the camera being detachably connected with the fuselage body of the mobile terminal, if the difference between the image parameters of the plurality ofpreview pictures does not meet the preset conditions, determining shooting parameters corresponding to a plurality of cameras respectively based on differences between image parameters of a pluralityof preview pictures, based on the shooting parameters corresponding to the plurality of cameras respectively, controlling the plurality of cameras to respectively collect images, and fusing the images respectively collected by the plurality of cameras to obtain fused images, so that the photograph effects synthesized by the plurality of cameras in the mobile terminal can be diversified and natural.
Owner:GUANGDONG OPPO MOBILE TELECOMM CORP LTD

Augmented reality-based human face interaction entertainment method

The invention discloses an augmented reality-based human face interaction entertainment method. The method comprises the following steps of 1, pre-building / pre-making a standard human face three-dimensional model and a face three-dimensional material; 2, inputting a human face video and detecting 2D human face feature points at each frame in the input human face video; 3, estimating 3D position and posture of a human face in video frames in combination with the standard human face three-dimensional model and the 2D human face feature points; 4, converting the pre-made face three-dimensional material to be in the same posture of the human face in the video according to the 3D position and posture, obtained in the step 3, of the human face, and performing rendering and superposition in the human face video to achieve an augmented reality effect; and 5, recording and storing an augmented reality effect video of the human face, and sharing the augmented reality effect video with friends for interaction. According to the method, the human face video can be shot only by a mobile phone camera without external devices such as a special sensor and the like; and the method is not limited in application range, is convenient for popularization, and has very good following performance and natural effects.
Owner:SUZHOU LIDUO DIGITAL TECH CO LTD

Signal lamp color effect enhancement processing method and apparatus thereof

The invention discloses a signal lamp color effect enhancement processing method and an apparatus thereof. The method and the apparatus are applied to an image processing system. The method comprises the following steps of extracting a reference RGB value from a signal lamp image; calculating color components of colors of all the pixels in a signal lamp area, wherein the colors match with display colors in the signal lamp area; then according to the calculated color components, carrying out corrosion processing on the signal lamp image, carrying out binarization processing on the signal lamp image which is not processed by a corrosion algorithm and on the signal lamp image which is processed by the corrosion algorithm and acquiring a different area of twice binarization processing; and taking the reference RGB value as a reference, selecting different color order parameter, calculating replaced RGB values of a foreground area and the different area acquired through the corrosion algorithm processing respectively, and then using a replaced RGB value of each pixel to replace an original RGB value of each pixel. The invention also discloses a signal lamp color effect enhancement processing apparatus. In the invention, signal lamp colors in a signal lamp image are easy to distinguish, an effect is nature and a lamp eye contour is clear.
Owner:济南宇视智能科技有限公司

Voice-driven 3D virtual human expression voice and picture synchronization method and system based on deep learning

The invention relates to a voice-driven 3D virtual human expression voice and picture synchronization method and system based on deep learning. The method comprises the following steps: extracting a logarithm amplitude spectrum in a voice signal as a voice signal characteristic; inputting the voice signal characteristic into a trained parameter prediction model which outputs an expression parameter value, wherein the parameter prediction model is a neural network model obtained by training a natural label pair relationship between a voice signal and an image signal in the video data; filteringthe expression parameter value output by the parameter prediction model; and performing image rendering of a 3D figure model by using the filtered expression parameter value to realize 3D virtual figure expression sound and picture synchronization. The system comprises a video analysis module, a parameter extraction module, a voice synthesis module, a voice signal processing module, a parameter prediction module, a parameter filtering module and a rendering module. According to the invention, the mouth lip effect of a virtual person is improved by learning a large amount of face video data such that the mouth lip effect is more natural and human-like.
Owner:超维视界(北京)传媒科技有限公司

Method and device for synthesizing facial expression image

The invention discloses a method and a device for synthesizing a facial expression image. The method comprises the steps that the expression features of at least two reference facial expression imagesare acquired; interpolation is performed on the expression features of at least two reference facial expression images so as to obtain new expression features; and the target facial expression imageis adjusted according to the new expression features so as to form the new facial expression image. According to the technical scheme, interpolation is performed on different expression features to obtain new expression features instead of directly amplifying or reducing the existing expression features, and the new facial expression image is obtained according to the new expression features. According to the technical scheme, the synthesized facial expression image effect is natural and the facial expression image is closer to the real expression image.
Owner:BEIJING SAMSUNG TELECOM R&D CENT +1

Robust automatic panoramic unmanned aerial vehicle image splicing method and device

The invention discloses a robust automatic panoramic unmanned aerial vehicle image splicing method and device. In a traditional automatic panoramic image splicing method, assuming that a camera precisely rotates around an optical center, transformation between source images is a group of special homography matrixes, such ideal data is difficult to obtain actually, especially, remote sensing imagesobtained by an unmanned aerial vehicle cannot meet such ideal conditions, that is, the images may not be on the same plane (including parallax), and even may suffer from non-rigid changes, resultingin bad splicing results. In order to overcome the challenges, a non-rigid matching algorithm is introduced into the splicing system, accurate feature matching is generated on a remote sensing image, and in the registration stage, the invention further provides a new differential transformation and overall adjustment strategy, so that the splicing system is suitable for the panoramic splicing effect of the unmanned aerial vehicle image. Experimental results show that the visual effect of the method is superior to that of a traditional method and some latest methods.
Owner:CHINA UNIV OF GEOSCIENCES (WUHAN)

Digital printing integration process

InactiveCN104908469AExcellent printing performanceShort processDyeing processOther printing apparatusDigital printingSizing
The invention relates to a digital printing integration process. The process specifically includes the steps of 1), for patterns to be printed, adopting computer scanning or directly inputting into a computer, and performing color separation processing by the aid of a computer printing color separation system to acquire the patterns of different passages; 2), according to the patterns of the different passages, performing combination to acquire standard design drawings of the required patterns and performing proofing on the patterns, wherein before proofing processing, the patterns of the different passages need to be configured with different sizing agents to be proofed; 3), for products qualified in printing proofing, performing subsequent processing to form the printing products meeting the requirements; 4), according to the requirements, performing configuration and sizing agent adjustment on the patterns of the different passages to form pattern products and printing products with different free combinations. With the method, printing integration can be realized, an existing printing technology process is changed, more excellent printing performance is achieved, and cost in printing design is greatly lowered.
Owner:张为海

Coating technique of paint removing effect carpentry

The invention relates to a coating technique and especially to an antique imitation technique. The coating technique of paint removing effect carpentry sequentially comprises the following technical steps: (1) checking sand of a material, (2) damaging, (3) sanding, (4) coating nitryl impression, (6) sanding, (7) forming an effect through size, (8) coating nitryl colored primer, (9) guaranteeing the effect, (10) coating a nitryl transparent primer, (11) performing dry burshing, (12) coating a nitryl transparent primer, (13) sanding and (14) coating nitryl finish. The coating technique of the paint removing effect carpentry has the advantages of better construction effect and better construction speed.
Owner:HUIZHOU CHANGRUNFA PAINT

Toon tree wood antiquing treatment agent

The invention relates to a toon tree wood antiquing treatment agent. The treatment agent consists of medicine liquid A, medicine liquid B and medicine liquid C, wherein the medicine liquid A is prepared by the following raw materials in parts by weight: 9.5 parts of folium isatidis, 7 parts of wild jujube leaves, 1.8 parts of divaricate saposhnikovia root, 3.2 parts of herba cepbalanoplosis segeti, 0.5 part of rhamnus utilis, 8 parts of quick lime, and 200 parts of water; the medicine liquid B is prepared by the following raw materials: 4 parts of rhizoma sparganii, 3.6 parts of radix stemonae, 4 parts of sandalwood, 2.5 parts of rhizoma alismatis, 7.2 parts of sodium hydrogen sulfate, and 120 parts of water; and the medicine liquid C is prepared by the following raw materials: 5 parts of sodium bicarbonate, and 150 parts of water. The toon tree wood antiquing treatment agent is prepared by mainly adopting traditional Chinese medicine components; and through reasonable matching and synergic effect between the traditional Chinese medicine components and inorganic components, the treatment effect is good, the antiquing effect is uniform and natural, textures are continuously distributed, the internal wood structure is free of corrosion, and the wood effects of corrosion resistance and insect resistance can be enhanced.
Owner:安徽省阜南志峰工艺品有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products