An image search method and apparatus, an electronic device and a storage medium. The image search method can be applied to an electronic device, which comprises a camera. The electronic device acquires an image to be matched, a first position of the electronic device and the azimuth of the camera, determines from a preset scene database a target preset area in which the first position is located and a target preset azimuth interval in which the azimuth is located, and searches for a corresponding target preset image set, thereby determining a target image for the image to be matched.

A training method for a robust neural network based on feature matching is provided in this disclosure, which includes following steps. Step A, a first stage model is initialized. The first stage model includes a backbone network, a feature matching module and a fullple loss function. Step B, the first stage model is trained by using original training data to obtain a second stage model. Step C, the second stage model is attacked so as to generate PGD adversarial samples of the original training data, and the second stage model is trained again with the generated adversarial samples and the original training data. Step D, training parameters are adjusted and the second stage model is trained again, and parameters for which the model has highest accuracy on an original test set are saved.

Methods and systems for providing an interactive image scene graph pattern search are provided. A user is provide with an image having a plurality of selectable segmented regions therein. The user selects one or more of the segmented regions to build a query graph. Via a graph neural network, matching target graphs are retrieved that contain the query graph from a target graph database. Each matching target graph has matching target nodes that match with the query nodes of the query graph. Matching target images from an image database are associated with the matching target graphs. Embeddings of each of the query nodes and the matching target nodes are extracted. A comparison of the embeddings of each query node with the embeddings of each matching target node is performed. The user interface displays the matching target images that are associated with the matching target graphs.

Embodiments of the invention are directed to a computer-implemented method of performing an electronic search. The computer-implemented method includes receiving, using a processor, a composite electronic image including a plurality of electronically identifiable objects, wherein the composite electronic image is associated with a user. The processor is used to segment the composite electronic image into sub-images by providing at least one of the sub-images for each of the plurality of electronically identifiable objects. For each of the sub-images, the processor is used to perform personalized sub-image search operations. The personalized sub-image search operations include selecting a sub-image-to-be-searched from among the sub-images; associating the sub-image-to-be-searched with personalized metadata of the user; and searching, based at least in part on the personalized metadata of the user, a database to return a set of search images.

Embodiments of the invention are directed to a computer-implemented method of performing an electronic search. The computer-implemented method includes receiving, using a processor, a composite electronic image including a plurality of electronically identifiable objects, wherein the composite electronic image is associated with a user. The processor is used to segment the composite electronic image into sub-images by providing at least one of the sub-images for each of the plurality of electronically identifiable objects. For each of the sub-images, the processor is used to perform personalized sub-image search operations. The personalized sub-image search operations include selecting a sub-image-to-be-searched from among the sub-images; associating the sub-image-to-be-searched with personalized metadata of the user; and searching, based at least in part on the personalized metadata of the user, a database to return a set of search images.

Described is a system and method for enabling dynamic selection of a search input. For example, rather than having a static search input box, the search input may be dynamically positioned such that it encompasses a portion of displayed information. An image segment that includes a representation of the encompassed portion of the displayed information is generated and processed to determine an object represented in the portion of the displayed information. Additional images with visually similar representations of objects are then determined and presented to the user.

Methods and apparatus for determining and/or using the image date, e.g., image capture date, of one or more scanned images based on image content is described. In various embodiments at least one object, e.g., face of a person, is identified in an image. The age of the object is determined, e.g., using age estimation techniques. The determined, e.g., estimated, age of the identified face is then compared to stored face age to image capture date information. Such information is obtained or derived from other images with known capture dates and including an image of the same object, e.g., face, as the image with the unknown date. Based on the estimated object age and stored information associating object age to image capture date, the image date, e.g., image capture date of the scanned image is determined. This information is then used to organize storage of the image with other images.

A system for driver identification includes an interface and a processor. The interface is configured to receive a trip; and receive a set of albums, wherein an album of the set of albums includes one or more existing trips. The processor is configured to determine similarities for the trip to all trips in the set of albums; determine a first clustering based at least in part on the similarities; indicate that the trip is a provisionally assigned trip that is provisionally assigned to the album of the set of albums based at least in part on the first clustering; determine a second clustering for a set of provisionally assigned trips and all trips in the set of albums, wherein the set of provisionally assigned trips comprises qualified provisionally assigned trips; and determine updated trip assignments for an updated set of albums.

A system for driver identification includes an interface and a processor. The interface is configured to receive a trip; and receive a set of albums, wherein an album of the set of albums includes one or more existing trips. The processor is configured to determine similarities for the trip to all trips in the set of albums; determine a first clustering based at least in part on the similarities; indicate that the trip is a provisionally assigned trip that is provisionally assigned to the album of the set of albums based at least in part on the first clustering; determine a second clustering for a set of provisionally assigned trips and all trips in the set of albums, wherein the set of provisionally assigned trips comprises qualified provisionally assigned trips; and determine updated trip assignments for an updated set of albums.

Example embodiments may provide a system, apparatus, computer readable media, and/or method configured for processing input representing data associated with a first product, the first product comprising a plurality of components, processing input representing a particular one of the components, processing input representing an attribute of the particular component or of the first product, querying a product memory based on the particular component and the attribute to identify a second product.