A method and system for face alignment. The method may include obtaining an image processing model set including M (M2) candidate models, and obtaining a test image including a target face. The method may also include conducting T (T1) stages of model set updating operation. Each stage of the T stages of model set updating operation may include conducting a performance evaluation to each candidate model of the image processing model set with respect to the test image, and updating the image processing model set by excluding at least one model from the image processing model set based on the performance evaluation. The method may further include designating, after completing the T stages of model set updating operation, at least one candidate model of the image processing model set as a target model, and determining, based on the target model, a result shape as a shape of the target face.

The specification describes methods and systems for increasing a dimensional depth of a two-dimensional image of a face to yield a face image that appears three dimensional. The methods and systems identify key points on the 2-D image, obtain a texture map for the 2-D image, determines one or more proportions within the 2-D image, and adjusts the texture map of the 3-D model based on the determined one or more proportions within the 2-D image.

In order to improve the learning performance of a neural network model, this image recognition model generating device is provided with an input image patch determining unit, a similar patch searching unit, a pixel value generating unit, and a convolution processing unit. The input image patch determining unit determines an input image patch containing a border region in contact with the outside of a boundary line of an input image. The similar patch searching unit searches for a similar patch that is similar to the input image patch. The pixel value generating unit generates a pixel value complementing the border region, on the basis of the similar patch. The convolution processing unit performs a convolution process from the generated pixel value and pixel values of the input image.

The present disclosure provides for improved image analysis via novel deblurring and segmentation techniques of image data. These techniques advantageously account for and incorporate segmentation of biological analytes into a deblurring process for an image. Thus, the deblurring of the image may advantageously be optimized for enabling identification and quantitative analysis of one or more biological analytes based on underlying biological models for those analytes. The techniques described herein provide for significant improvements in the image deblurring and segmentation process which reduces signal noise and improves the accuracy of the image. In particular, the system and methods described herein advantageously utilize unique optimization and tissue characteristics image models which are informed by the underlying biology being analyzed, (for example by a biological model for the analytes). This provides for targeted deblurring and segmentation which is optimized for the applied image analytics.

Predicting patch displacement maps using a neural network is described. Initially, a digital image on which an image editing operation is to be performed is provided as input to a patch matcher having an offset prediction neural network. From this image and based on the image editing operation for which this network is trained, the offset prediction neural network generates an offset prediction formed as a displacement map, which has offset vectors that represent a displacement of pixels of the digital image to different locations for performing the image editing operation. Pixel values of the digital image are copied to the image pixels affected by the operation.

An image processing apparatus is described comprising a processor configured to access a template of image elements. The processor is configured to search an image which is larger than the template to find a region which is similar to the template, where similarity is measured using a similarity metric. The similarity metric comprises a normalized cross correlation function which is modified to include at least one factor related to a statistic of both the template and the region.

Predicting patch displacement maps using a neural network is described. Initially, a digital image on which an image editing operation is to be performed is provided as input to a patch matcher having an offset prediction neural network. From this image and based on the image editing operation for which this network is trained, the offset prediction neural network generates an offset prediction formed as a displacement map, which has offset vectors that represent a displacement of pixels of the digital image to different locations for performing the image editing operation. Pixel values of the digital image are copied to the image pixels affected by the operation by: determining the vectors pixels that correspond to the image pixels affected by the image editing operation and mapping the pixel values of the image pixels represented by the determined offset vectors to the affected pixels. According to this mapping, the pixel values of the affected pixels are set, effective to perform the image editing operation.

The present invention discloses methods and systems for recognizing an object in an input image based on stored training images. An object recognition system the input image, computes a signature of the input image, compares the signature with one or more stored signatures and retrieves one or more matching images from the set of training images. The matching images are then displayed to the user for further action.

The specification describes methods and systems for increasing a dimensional depth of a two-dimensional image of a face to yield a face image that appears three dimensional. The methods and systems identify key points on the 2-D image, obtain a texture map for the 2-D image, determines one or more proportions within the 2-D image, and adjusts the texture map of the 3-D model based on the determined one or more proportions within the 2-D image.

Combinatorial shape regression is described as a technique for face alignment and facial landmark detection in images. As described stages of regression may be built for multiple ferns for a facial landmark detection system. In one example a regression is performed on a training set of images using face shapes, using facial component groups, and using individual face point pairs to learn shape increments for each respective image in the set of images. A fern is built based on this regression. Additional regressions are performed for building additional ferns. The ferns are then combined to build the facial landmark detection system.