A system and method for determining a facial expression including a facial mask generator arranged to detect a plurality of facial points from one or more facial images to generate one or more associated facial point masks, arranged to represent the facial features of an associated face of the one or more facial images; and a learning network arranged to receive and input of the one or more facial images and the one or more associated facial point masks to obtain a classification result for each of the one or more facial images, wherein the classification result is one of a plurality of predefined facial expressions.

Digital imaging systems and methods are described for analyzing pixel data of an image of a skin area of a user for determining skin puffiness. A plurality of training images of a plurality of individuals are aggregated, each of the training images comprising pixel data of a respective skin area of an individual. A skin puffiness model, trained with the pixel data, is operable to output, across a range of a skin puffiness scale, skin puffiness values associated with a degree of skin puffiness. An image of a user comprising pixel data of at least a portion of a user skin area is received and analyzed, by the skin puffiness model, to determine a user-specific skin puffiness value of the user skin area. A user-specific electronic recommendation addressing at least one feature identifiable within the pixel data is generated and rendered, on a display screen of a user computing device.

Approaches are described which enable a computing device (e.g., mobile phone, tablet computer) to utilize one or more facial recognition techniques to control access to the device and to detect when artificial representations of a user, such as a picture or photograph, are being used in an attempt to gain access to the device. Evidence indicative of artificial representations may include lack of changes in facial skin color between multiple images captured by a camera, ability to track one or more features of the human face while the camera is rotated or moved, presence of secular reflections caused by an illumination device, absence of shadows in the image, and others.

Systems and methods herein are developed which enable modification of an initial customized cosmetic product, wherein the initial customized cosmetic product is created based on an initial customized cosmetic product specification or an existing specification of a non-custom product. One such system and method for making a custom cosmetic product from an existing non-custom cosmetic product is configured to be capable of: characterizing a non-custom product with a known key comprised of at least one search component; providing user interaction to modify at least one of the at least one search components in this key to create a modified key; and using the modified key to produce custom product which may include determining manufacturing instructions. Such systems and methods may incorporate a custom or non-custom product attribute data base for providing product attribute data for modification and adjustment of the user search key using an adjustment service. Also incorporated herein are applications based on user interaction through two-dimensional complexion color maps derived using data associated with skin color, tone, morphology and/or biochemistry from a plurality of users.

Methods and systems for fully-automatic image processing to detect and remove unwanted people from a digital image of a photograph. The system includes the following modules: 1) Deep neural network (DNN)-based module for object segmentation and head pose estimation; 2) classification (or grouping) of wanted versus unwanted people based on information collected in the first module; 3) image inpainting of the unwanted people in the digital image. The classification module can be rules-based in an example. In an example, the DNN-based module generates, from the digital image: 1. A list of object category labels, 2. A list of object scores, 3. A list of binary masks, 4. A list of object bounding boxes, 5. A list of crowd instances, 6. A list of human head bounding boxes, and 7. A list of head poses (e.g., yaws, pitches, and rolls).

Systems, devices, media, and methods are presented for segmenting an image of a video stream with a client device, binarizing an area of interest within one or more image, identifying an initial pupil location and an initial iris radius, and determining a final pupil location and a final iris radius. Some embodiments enable the client device to perform one or more operations within a user interface based on the image segmentation.

A portable custom cosmetic pigment dispenser creates a cosmetic pigment mixture that closely matches a person's skin color. The device is constructed with a color sensor at one end that scans the skin and records color values in a color space. A processor converts the color values into a colorspace. In one example, a user is presented with a sample of the color as determined by the processor and has an opportunity to accept or modify the color. Specific quantities of colored pigment are selected based on the corresponding weightings in the color space.

An image processing apparatus includes an image input that receives input of image data of a captured human being, a region detector that detects a specific color region of the image data, a filter that smooths a pixel value in the specific color region detected by the region detector by using a frame of the image data input into the image input and each of previous and subsequent frames of the image data of the inputting into the image input, a coder that codes an output image of the filter, and an output that outputs the output image of the filter coded by the coder.

A thermal image positioning method for determining a heat source location of the thermal image is disclosed. The thermal image positioning method includes obtaining a temperature array corresponding to the thermal image and determining a region of interest (ROI) of the temperature array. The thermal image positioning method further includes determining an ROI center reference point of the ROI, determining a plurality of corner points corresponding to the ROI, and determining the heat source location according to at least one of the plurality of corner points. A thermal image positioning system is also disclosed herein.

Disclosed is an electronic device. There electronic device according to an embodiment includes: a memory; and a processor electronically connected to the memory, wherein the processor can be configured to recognize a face region from an image, check first skin probability data, corresponding to a region to be corrected, on the basis of a first skin color distribution including a skin color distribution stored in association with a plurality of races, first color data of the face region, and a second color data of the region to be corrected which is in the image and includes the face region, determine a category of the face region on the basis of the first color data of the face region, and correct the color, of the region to be corrected, on the basis of the determined category and the first skin probability data. Various other embodiments understood from the specification are also possible.