According to implementations of the subject matter described herein, there is provided a solution for text recognition in an image. In this solution, a target text line area, which is expected to include a text to be recognized, is determined from an image. Probability distribution information of a character model element(s) present in the target text line area is determined using a single character model. The single character model is trained based on training text line areas and respective ground-truth texts in the training text line areas. Texts in the training text line areas are arranged in different orientations, and/or the ground-truth texts comprise texts are related to various languages (e.g., texts related to a Latin and an Eastern languages). The text in the target text line area can be determined based on the determined probability distribution information. The single character model enables more efficient and convenient text recognition.

A computer system for detecting a target video from a sports video based on voice recognition is configured to convert a relay voice corresponding to a sports video to text; and to detect a target video related to a preset event from the sports video based on the text.

A method for adjusting an audio transmission when a user of the system is being spoken to by another person includes receiving audio signals representative of sounds from an environment of the user captured by at least one microphone; determining at least from the received audio signals that the another person is speaking to user; and subject to the user being spoken to by the another person, adjusting the audio transmission to the user and signaling to the user that the user is being spoken to.

Techniques for meter text detection and recognition are described herein. In an example, an application receives a first image, depicting information displayed by the meter, from an imaging device. One or more qualities of the first image may be assessed, such as focus or lighting. A setting of the imaging device may be adjusted. The adjusting may be based at least in part on the assessed quality of the first image and one or more characteristics of an optical character recognition (OCR) algorithm. Accordingly, the settings of the image-capture device are tuned to the needs of the OCR algorithm. A second image may be captured, depicting information displayed by the meter, using the imaging device adjusted according to the adjusted setting. The OCR algorithm may be applied to the second image to obtain an alphanumeric value associated with the second image. The alphanumeric value is obtained from the OCR algorithm.

Aspects of the present disclosure are directed to extracting textual information from image documents. In one embodiment, a system, upon receiving a request to extract textual information from an image document, a digital processing system performs character recognition based on content of the image document using multiple approaches to generate corresponding texts. The texts are then combined to determine a result text representing the textual information contained in the image document. The result is then provided as a response to the request.

Systems and methods relating to displaying images are disclosed. In one embodiment, sensor data is received via one or more sensors of a wearable head device comprising a display, the sensor data indicative of a surrounding environment of a user of the wearable head device. An image can be determined based on the sensor data, the image corresponding to the surrounding environment. A visibility of a first portion of the image corresponding to a first portion of the surrounding environment can be enhanced. Enhancing a visibility of a second portion of the image corresponding to a second portion of the surrounding environment can be forgone. The enhanced first portion of the image and a view of the second portion of the surrounding environment can be presented concurrently via the display of the wearable head device.

Present disclosure provides a method and system for package movement visibility in warehouse operations. The method includes identifying, by the package management system (1000), an object entering AOE and moving in a predetermined direction and recording, by the package management system (1000), image frame of the object. The method also includes determining, by the package management system (1000), that the object in the image frame is a package and determining, by the package management system (1000), a label on the package from the image frame. Further, the method also includes determining, by the package management system (1000), a match to the label in a cloud platform (400) and sending, by the package management system (1000), tracking details associated with the package based on the match to the label in the cloud platform (400), to a client device in real-time.

Real-time video is captured of a pickup area for orders at a store. The images are analyzed and tracked for unique orders being placed in the pickup area and orders being removed from the pickup area. A customer-operated device is operated by a customer to identify the store where the customer placed an order in a remote location from the pickup area. Images of the orders that are present within the pickup area and order identifying information for the orders are provided to the customer via the customer-operated device.

The techniques described herein relate to computerized methods and apparatuses for detecting objects in an image. The techniques described herein further relate to computerized methods and apparatuses for detecting one or more objects using a pre-trained machine learning model and one or more other machine learning models that can be trained in a field training process. The pre-trained machine learning model may be a deep machine learning model.

A method for selection of a marker in an augmented reality (AR) environment is provided. The method includes capturing a scene in the augmented reality environment; extracting a set of region of interest from the scene captured; identifying a text in the region of interest or from a document associated to the region of interest; determining a set of phrase-action pairs from the text; generating a representation of a set of region of interest and a representation of a set of phrase-action pairs; calculating inter model similarity using the set of region of interest and the set of phrase-action pairs in common embedding space; computing intra model similarity by comparing the extracted ROI with a generated ROI and the extracted phrase-action with generated phrase actions; and selecting a phrase-action-ROI tuple having the highest intra modal similarity as the marker.