Apical Ltd. | Date: 2016-09-14
The present disclosure provides an adaptive shading correction method for correcting an image for lens shading, including segmenting the image into a plurality of blocks of pixels and identifying hue-flat blocks with a relatively low hue variance, where the hue-flat blocks are clustered into at least one cluster based on a spatial distribution of the blocks. Selected modification parameters for modifying an average shading mesh are identified by modifying the average shading mesh along a plurality of dimensions using a plurality of modification parameters, and processing the at least one cluster with the average shading mesh as modified so as to identify the selected modification parameters. The average shading mesh is modified using the selected modification parameters to generate a shading correction mesh, which is used to correct the image for lens shading.
APICAL Ltd | Date: 2015-12-18
The invention relates to feature extraction technique based on edge extraction. It can be used in computer vision systems, including image/facial/object recognition systems, scene interpretation, classification and captioning systems. A model or profile of the noise in the sensor is used to improve feature extraction or object detection on an image from a sensor.
Apical Ltd | Date: 2015-08-13
A method to frame a video stream is provided. A video stream is captured, then motion of the camera, object presence in the video stream, and position of the object are detected. A framed video stream is generated using a framing in dependence on the motion of the camera and the position of the object. A system for framing a video stream is also provided, wherein the system comprises a camera and a processing unit, and the processing unit comprises at least one processor and at least on memory including computer program instructions to execute a method to frame a video stream.
Apical Ltd | Date: 2015-09-03
A method to analyze an image and determine whether to output image data associated with an area of the image is provided. An object detection algorithm using training image data to detect an object based at least in part on a similarity of appearance of image data to data derived from the training image data is provided. Weakly detected objects are classified based on characteristics associated with the weakly detected object and may be added to the training image dataset for use in further training of the object detection algorithm. The object detection algorithm is trained with a revised dataset, the revised dataset being updated with data generated by the object detection algorithm.
Apical Ltd. | Date: 2015-07-16
A method for analyzing a video stream is provided. The method determines a set of two or more frames containing an object, and generates an object record describing time evolution of at least one characteristic of the object. An apparatus comprising a processor and a memory to perform this method is also provided.
Apical Ltd | Date: 2015-01-29
A method of selecting at least one region of interest within an image includes the selection of a preliminary region having a preliminary border. The selection uses one or more characteristics of the image. An inner probability distribution of color components is determined within the preliminary region and an outer probability distribution of color components outside the preliminary region. The preliminary border is adjusted in dependence on the probability distributions, the adjusted border defining the at least one region of interest.
Apical Ltd | Date: 2014-02-21
A method of controlling in a display device screen brightness and strength of dynamic range compression of display data in dependence on ambient light level. Ambient light level values are required from one or more ambient light sensors. The ambient light level values are averaged using a first method to obtain a first average value and using a second, different method to obtain a second average value. The first average value is used for controlling the screen brightness and the second average value is used for controlling the strength of the dynamic range compression.
Apical Ltd. | Date: 2015-01-20
A method of determining an orientation of an object within an image. The method determines the responses of at least two classifiers in at least one region of the image corresponding to the object. The classifiers have been trained to identify a given object in different specific orientations. The orientation of the object is determined as an average of the specific orientations, weighted by the responses of their respective classifiers.
Apical Ltd. | Date: 2015-05-12
In a method of enhancing the appearance of a digital image on an electronic display, Ambient Light Sensor (ALS) and Screen Brightness (SB) inputs are combined with a calibration input 12 to generate a first strength parameter 22, including an alpha component that is dependent only upon the properties of the display. Then a further, content-based input 24 is also combined to generate a second strength parameter 26, including a beta component that is dependent only upon a content type, or a content quality, or both.
Apical Ltd | Date: 2015-03-16
A method of forming a control parameter dependent on ambient light. The method comprises the steps of acquiring light values from an ambient light sensor and acquiring positional status values from a positional status sensor. The control parameter depends on the light values and is filtered in dependence on the positional status values.