The present invention enables highly accurate analysis when visualizing analysis results in spectral imaging.

An surface analysis method includes: acquiring spectral image data regarding a sample surface with use of a spectral camera; extracting n wavelengths dispersed in a specific wavelength range in the acquired spectral image data, and converting spectrums of the wavelengths in the spectral image data into n-dimensional spatial vectors for each pixel; normalizing the spatial vectors of the pixels; clustering the normalized spatial vectors into a specific number of classifications; and identifying and displaying pixels clustered into the classifications, for each of the classifications.

The present invention enables highly accurate analysis when visualizing analysis results in spectral imaging.

An surface analysis method includes: acquiring spectral image data regarding a sample surface with use of a spectral camera; extracting n wavelengths dispersed in a specific wavelength range in the acquired spectral image data, and converting spectrums of the wavelengths in the spectral image data into n-dimensional spatial vectors for each pixel; normalizing the spatial vectors of the pixels; clustering the normalized spatial vectors into a specific number of classifications; and identifying and displaying pixels clustered into the classifications, for each of the classifications.

In order to acquire recognition environment information impacting the recognition accuracy of a recognition engine, an information processing device 100 comprises a detection unit 101 and an environment acquisition unit 102. The detection unit 101 detects a marker, which has been disposed within a recognition target zone for the purpose of acquiring information, from an image captured by means of an imaging device which captures images of objects located within the recognition target zone. The environment acquisition unit 102 acquires the recognition environment information based on image information of the detected marker. The recognition environment information is information representing the way in which a recognition target object is reproduced in an image captured by the imaging device when said imaging device captures an image of the recognition target object located within the recognition target zone.

In order to acquire recognition environment information impacting the recognition accuracy of a recognition engine, an information processing device 100 comprises a detection unit 101 and an environment acquisition unit 102. The detection unit 101 detects a marker, which has been disposed within a recognition target zone for the purpose of acquiring information, from an image captured by means of an imaging device which captures images of objects located within the recognition target zone. The environment acquisition unit 102 acquires the recognition environment information based on image information of the detected marker. The recognition environment information is information representing the way in which a recognition target object is reproduced in an image captured by the imaging device when said imaging device captures an image of the recognition target object located within the recognition target zone.

An urban remote sensing image scene classification method in consideration of spatial relationships is provided and includes following steps of: cutting a remote sensing image into sub-images in an even and non-overlapping manner; performing a visual information coding on each of the sub-images to obtain a feature image Fv; inputting the feature image Fv into a crossing transfer unit to obtain hierarchical spatial characteristics; performing convolution of dimensionality reduction on the hierarchical spatial characteristics to obtain dimensionality-reduced hierarchical spatial characteristics; and performing a softmax model based classification on the dimensionality-reduced hierarchical spatial characteristics to obtain a classification result. The method comprehensively considers the role of two kinds of spatial relationships being regional spatial relationship and long-range spatial relationship in classification, and designs three paths in a crossing transfer unit for relationships fusion, thereby obtaining a better urban remote sensing image scene classification result.

An urban remote sensing image scene classification method in consideration of spatial relationships is provided and includes following steps of: cutting a remote sensing image into sub-images in an even and non-overlapping manner; performing a visual information coding on each of the sub-images to obtain a feature image Fv; inputting the feature image Fv into a crossing transfer unit to obtain hierarchical spatial characteristics; performing convolution of dimensionality reduction on the hierarchical spatial characteristics to obtain dimensionality-reduced hierarchical spatial characteristics; and performing a softmax model based classification on the dimensionality-reduced hierarchical spatial characteristics to obtain a classification result. The method comprehensively considers the role of two kinds of spatial relationships being regional spatial relationship and long-range spatial relationship in classification, and designs three paths in a crossing transfer unit for relationships fusion, thereby obtaining a better urban remote sensing image scene classification result.

Disclosed is a method for training shallow convolutional neural networks for infrared target detection using a two-phase learning strategy that can converge to satisfactory detection performance, even with scale-invariance capability. In the first step, the aim is to ensure that only filters in the convolutional layer produce semantic features that serve the problem of target detection. L2-norm (Euclidian norm) is used as loss function for the stable training of semantic filters obtained from the convolutional layers. In the next step, only the decision layers are trained by transferring the weight values in the convolutional layers completely and freezing the learning rate. In this step, unlike the first, the L1-norm (mean-absolute-deviation) loss function is used.

A multi-task deep learning-based real-time matting method for non-green-screen portraits is provided. The method includes: performing binary classification adjustment on an original dataset, inputting an image or video containing portrait information, and performing preprocessing; constructing a deep learning network for person detection, extracting image features by using a deep residual neural network, and obtaining a region of interest (ROI) of portrait foreground and a portrait trimap in the ROI through logistic regression; and constructing a portrait alpha mask matting deep learning network. An encoder sharing mechanism effectively accelerates a computing process of the network. An alpha mask prediction result of the portrait foreground is output in an end-to-end manner to implement portrait matting. In this method, green screens are not required during portrait matting. In addition, during the matting, only original images or videos need to be provided, without a need to provide manually annotated portrait trimaps.

Techniques are disclosed for changing the identities of faces in images. In embodiments, a tunable model for changing facial identities in images includes an encoder, a decoder, and dense layers that generate either adaptive instance normalization (AdaIN) coefficients that control the operation of convolution layers in the decoder or the values of weights within such convolution layers, allowing the model to change the identity of a face in an image based on a user selection. A separate set of dense layers may be trained to generate AdaIN coefficients for each of a number of facial identities, and the AdaIN coefficients output by different sets of dense layers can be combined to interpolate between facial identities. Alternatively, a single set of dense layers may be trained to take as input an identity vector and output AdaIN coefficients or values of weighs within convolution layers of the decoder.

A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the device segments the image into a region of interest that includes information useful for classification and a background region by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.