Approaches are described for shape-based graphics search. Each graphics object of a set of graphics objects is analyzed. The analyzing includes determining an outline of the graphics object from graphics data that forms the graphics object. The outline of the graphics object is sampled resulting in sampled points that capture the outline of the graphics object. A shape descriptor of the graphics object is determined which captures local and global geometric properties of the sampled points. Search results of a search query are determined based on a comparison between a shape descriptor of a user identified graphics object and the shape descriptor of at least one graphics object of the set of graphics objects. At least one of the search results can be presented on a user device associated with the search query.

A system for determining a road type includes processing circuitry configured to receive information from a plurality of sensors. The information corresponds to one or more of operation of a host vehicle and an environment surrounding the host vehicle. Additionally, the system determines whether one or more of the plurality of sensors detects an off highway event, classifies the road type as a local road in response to one or more of the plurality of sensors detecting an off highway event, determines whether the speed of the host vehicle is greater than a first predetermined speed for a first predetermined amount of time, and classifies the road type as a limited access highway in response to the speed of the host vehicle being greater than the first predetermined speed for the first predetermined amount of time.

A headphone for spatial audio rendering includes a first database having an impulse response pair corresponding to a reference speaker location. A head sensor provides head orientation information to a second database having rotation filters, the filters corresponding to different azimuth and elevation positions relative to the reference speaker location. A digital signal processor combines the rotation filters with the impulse response pair to generate an output binaural audio signal to transducers of the headphone. Efficiencies in creating impulse response or HRTF databases are achieved by sampling the impulse response less frequently than in conventional methods. This sampling at coarser intervals reduces the number of data measurements required to generate a spherical grid and reduces the time involved in capturing the impulse responses. Impulse responses for data points falling between the sampled data points are generated by interpolating in the frequency domain.

A method for checking a marking of a product. In an image acquisition step (3) at least one image (4) of the marking arranged on a surface of the product is acquired by a calibrated test camera, and in a layout checking step (1), using the at least one recorded image (4), the quality of the marking applied on the surface is checked with respect to static data such as position and machine-readability. Using the at least one image (4) recorded by the test camera, in addition to the checking of the quality of the marking in the layout checking step (1), in a code checking step (2), variable product information (12) contained in the marking is acquired and the acquired variable product information is compared with reference information from a reference information database (13). A correspondence characteristic is determined by means of the comparison.

Methods and systems for diagnosing semiconductor wafer are provided. A target image is obtained according to graphic data system (GDS) information of a specific layout in the semiconductor wafer, wherein the target image includes a first contour having a first pattern corresponding to the specific layout. Image-based alignment is performed to capture a raw image from the semiconductor wafer according to the first contour. The semiconductor wafer is analyzed by measuring the raw image, so as to provide a diagnostic result.

A medical imaging device includes: a display configured to display first and second medical images having different modalities from each other with respect to an object: an image processor configured to match the first and second medical images, extract a second object corresponding to a first object selected in the first medical image from the second medical image, extract first feature information of the first object by analyzing the first medical image, and extract second feature information of the second object by analyzing the second medical image: and a controller configured to generate final diagnostic information based on the first and second feature information, and control the display to display the final diagnostic information.

In an example, a first machine learning algorithm is used to train a smart contour model to identify contours of product shapes in input images and to identify backgrounds in the input images. A second machine learning algorithm is used to train a plurality of shape-specific classification models to output identifications of products in input images. A candidate image of one or more products is obtained. The candidate image is passed to the smart contour model, obtaining output of one or more tags identifying product contours in the candidate image. The candidate image and the one or more tags are passed to an ultra-large scale multi-hierarchy classification system to identify one or more classification models for one or more individual product shapes in the candidate image. The one or more classification models are used to distinguish between one or more products and one or more unknown products in the image.

In an example, a computerized neural fabric is created by representing each pattern of learned weights of one or more machine learning algorithm-trained models specifying a specific set of products as a column in the computerized neural fabric, each pattern comprising one or more clusters representing combinations of convolutional filters, each cluster learning low level features and sending output via a vertical flow up the corresponding column to a final classification within the corresponding pattern. One or more potential lateral flows between patterns in the computerized neural fabrics is dynamically determined based on resemblance of a new product in a candidate image to the specific sets of products in each of the patterns and identifying possible mutations of the patterns based on the resemblance. Then, one of the one or more potential lateral flows is selected as a new model.

The disclosure discloses a method and device for image recognition. The method comprises: placing instruction blocks in a required order; acquiring an encoded instruction block image that represents the instruction block pattern and the placement order; recognizing a single instruction block image from the encoded instruction block image; comparing the single instruction block image with a standard instruction block image to obtain the matching degree of the instruction block; determining, according to the matching degree, standard instruction blocks corresponding to respective instruction block images; sorting the instruction block images according to the coordinates in the encoded instruction block image; parsing the instruction block images according to the sorting order to obtain instructions. The method for image recognition can help children learning concepts such as manipulation, use and programming of intelligent programmable devices more easily.

A nail contour detecting device including a processor, wherein the processor obtains first feature point data of a first nail contour which is a nail contour detected from a first nail image obtained by imaging a nail of a finger or a toe, and second feature point data of a second nail contour which is a nail contour detected from a second nail image obtained by imaging a nail of the same finger or toe as the first nail image; and the processor obtains one nail contour based on the first feature point data and the second feature point data.