Abstract

The present disclosure relates to the technical field of artificial intelligence, and provides a head size measurement method and a 3D head grid generation method. According to the method, a face local area is determined by means of face feature points, a circular reference object is extracted from the face local area, and a head size of a target object is determined on the basis of the size of the circular reference object, thereby generating a 3D head grid. The accuracy is high.

IPC Classes  ?

• G06T 17/00 - 3D modelling for computer graphics

Abstract

The present disclosure belongs to the technical fields of computers and defect detection. Provided are a defect detection method and a related device. The method comprises: obtaining an image to be processed; processing said image by means of a feature extraction module in a deep-learning defect detection model, wherein the feature extraction module comprises an intermediate feature layer, the intermediate feature layer comprises a dropout layer, and the dropout layer is configured to randomly drop features which are extracted by means of the intermediate feature layer processing said image, such that a plurality of features subjected to random dropout are obtained after said image is processed by means of the feature extraction module; by means of a detection head in the deep-learning defect detection model, processing the plurality of features subjected to random dropout, so as to obtain a plurality of category prediction results and a plurality of position prediction results of defects in said image; and obtaining category detection results, position detection results, category uncertainties and position uncertainties of the defects in said image according to the plurality of category prediction results and the plurality of position prediction results of the defects. (FIG. 1)

IPC Classes  ?

• G06T 7/00 - Image analysis

Abstract

The present disclosure provides a font generation model training method and a related device. The method comprises: obtaining a sample text image of a reference font, description information of a target font and a target text image of the target font, wherein the sample text image and the target text image comprise the same text; inputting the sample text image of the reference font and the description information of the target font into a font generation model to be trained, so as to obtain a predicted text image of the target font; and according to the predicted text image of the target font and the target text image of the target font, training a generative adversarial network comprising the font generation model and a discrimination network, so as to obtain a trained font generation model.

IPC Classes  ?

• G06V 30/19 - Recognition using electronic means

Abstract

Provided are a printing defect detection method and apparatus, and a device and a storage medium, which relate to the technical field of computers. The method comprises: acquiring an initial target image of a printed product to be subjected to detection; acquiring a reference image corresponding to said printed product; aligning the initial target image with the reference image in a plurality of modes, so as to respectively obtain a plurality of candidate transformed target images; determining a transformed target image on the basis of the degree of similarity between each of the plurality of candidate transformed target images and the reference image; performing color distribution feature standardization processing on the transformed target image on the basis of the reference image, so as to obtain a standardized transformed target image; and obtaining a final difference result on the basis of the standardized transformed target image and the reference image, so as to detect a printing defect of said printed product according to the final difference result.

IPC Classes  ?

• G06T 7/00 - Image analysis

Abstract

An intelligent cloth inspection detection system and method, and a readable medium and a product. A cloud server end (11) is connected to a plurality of cloth inspection machine clients (12), and receives a plurality of pieces of detection result information, which are sent by the plurality of cloth inspection machine clients (12), so as to obtain defect information of cloth corresponding to each cloth inspection machine client (12), such that a workplace of a cloth inspection worker can be changed from a cloth inspection workshop to a remote office, and the parallel management of a plurality of cloth inspection machines by fewer workers is realized; thus, the cloth detection efficiency is greatly improved.

IPC Classes  ?

• G01N 21/898 - Irregularities in textured or patterned surfaces, e.g. textiles, wood
• G01N 21/01 - Arrangements or apparatus for facilitating the optical investigation

Abstract

Provided are a jacquard knitted fabric allowing for multiple surface pattern designs, and a weaving method. The jacquard knitted fabric is formed by circularly weaving a plurality of knit units. Each knit unit has a front side (68) and a back side (69), and comprises a plurality of weft yarns, wherein each weft yarn is alternately woven in the front side (68) and the back side (69); each weaving line of the back side (69) comprises a plurality of loops/tucks and floating threads; loops and/or tuck columns and floating thread columns are alternately arranged in multiple weaving columns of the back side (69); and the loops located in the same weaving column of the back side (69) are reversely interlaced together.

IPC Classes  ?

• D04B 1/10 - Patterned fabrics or articles
• D04B 1/00 - Weft knitting processes for the production of fabrics or articles not dependent on the use of particular machinesFabrics or articles defined by such processes
• D04B 9/00 - Circular weft knitting machines with independently-movable needles

Abstract

A system for human-computer interaction and a textile for human-computer interaction. The system comprises: an image collection device, a micro-single-board computer, a light-source device and a textile, wherein the image collection device is used for collecting a biological-feature image; the micro-single-board computer is used for controlling, according to a recognition result of the biological-feature image, the light-source device to emit visible light of a target color; and the textile comprises light-emitting tissue, wherein the visible light of the target color, which is emitted by the light-source device, is transmitted by means of the light-emitting tissue, such that the textile presents the target color.

IPC Classes  ?

• G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
• G06N 3/04 - Architecture, e.g. interconnection topology

Abstract

A textile defect detection system, comprising: a transmission assembly (10), which is suitable for textile conveyance and comprises a first transmission section (102) and a second transmission section (104); an image acquisition assembly (20), which comprises a first frame (202) and a camera array (204), the camera array (204) acquiring an image of a textile passing through the first transmission section (102); an inspection assembly (30) opposite to the second transmission section (104); a control apparatus (40), which is electrically connected to the camera array (204) and suitable for receiving the image of the textile acquired by the camera array (204), and generates a marking instruction when detecting that there is a defect on the image of the textile; and a marking apparatus (50), which is provided at an output end of the transmission assembly (10), electrically connected to the control apparatus (40), and suitable for marking a textile defect on the basis of the marking instruction output by the control apparatus (40). A detection approach for textile defects in which machine inspection and manual detection are both taken into consideration is achieved, thereby facilitating the improvement of the accuracy of detecting the textile defects.

IPC Classes  ?

• G01N 21/898 - Irregularities in textured or patterned surfaces, e.g. textiles, wood

Abstract

Provided in the present application are a method and apparatus for intelligent clothing matching, and an electronic device and a storage medium. The method comprises: acquiring a first clothing image and a second clothing image; performing feature extraction on the first clothing image and the second clothing image, so as to obtain a feature value of a first clothing element of the first clothing image, a feature value of a second clothing element of the first clothing image, a feature value of a first clothing element of the second clothing image and a feature value of a second clothing element of the second clothing image; determining a first matching compatibility and a second matching compatibility between the first clothing image and the second clothing image; generating a clothing matching compatibility and a matching level between the first clothing image and the second clothing image according to the first matching compatibility and the second matching compatibility; and generating a clothing matching combination. By means of the method, a clothing matching combination having a better matching effect can be automatically generated according to a clothing matching compatibility and a matching level of clothing images, thereby improving the efficiency of generating the clothing matching combination, and improving the user experience.

IPC Classes  ?

• G06F 16/535 - Filtering based on additional data, e.g. user or group profiles

Abstract

A color unit determination method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a color value range of a plurality of initial color units and colors comprised in the initial color units (S202); determining, according to a color value of each color comprised in each initial color unit, a maximum color difference value between the initial color units (S204); if the maximum color difference value between the initial color units does not satisfy a preset condition, adjusting the color value range of the initial color units and the colors comprised in the initial color units (S206); and if the maximum color difference value between the initial color units satisfies the preset condition, determining the initial color units as target color units (S208). According to the method, more accurate target color units can be obtained, so that the accuracy of color matching according to the target color units is improved, and a matching effect of color related tasks is improved.

IPC Classes  ?

• G06T 7/90 - Determination of colour characteristics