In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed viewsfurther minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and usedor ignoredin product identification. A great variety of other features and arrangements are also detailed.

Systems and methods for optical sensing, visualization and detection in media (e.g., turbid media; turbid water; fog; non-turbid media). A light source and an image sensor are positioned in turbid media or external to the turbid media with the light source within a field of view of the image sensor array. Temporal optical signals are transmitted through the turbid media via the light source and multiple perspective video sequence frames are acquired via the image sensor array of light propagating through the turbid media. A three-dimensional image is reconstructed from each frame and the reconstructed three-dimensional images are combined to form a three-dimensional video sequence. The transmitted optical signals are detected from the three-dimensional video sequence by applying a multi-dimensional signal detection scheme.

An object recognition device according to an embodiment includes a camera that captures an image of an imaging area. A storage device stores, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object. A processor receives the captured image from the camera, and determines an object area in the captured image. The processor extracts feature information from the object area, and, based on the extracted feature information compared to the dictionary feature information, identifies each object included in the object area. The processor also extracts boundary information corresponding to each identified object included in the object area, and, based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determines an overlap state of each identified object in the object area.

Disclosed are a mobile device and method which include acquiring, by an image acquisition unit installed in a mobile device, an image of eyes of a patient while light provided by a light source reflects from an optical surface of the eyes of the patient; and obtaining, by a processor installed in the mobile device, ocular misalignment measurements, including a magnitude and a direction of ocular misalignment in the eyes of the patient, using the acquired image or set of images.

A multi-camera vision system and method of monitoring. In one embodiment imaging systems provide object classifications with cameras positioned to receive image data from a field of view to classify an object among multiple classifications. A control unit receives classification or position information of objects and (ii) displays an image corresponding to a classified object relative to the position of the structure. An embodiment of a related method monitors positions of an imaged object about a boundary by continually capturing at least first and second series of image frames, each series comprising different fields of view of a scene about the boundary, with some of the image frames in the first series covering a wide angle field of view and some of the image frames in the second series covering no more than a narrow angle field of view.

A laser generator is provided. The laser generator includes a substrate and an array of light-emitting elements. The array of light-emitting elements is arranged on the substrate. The array of light-emitting elements includes a basic array and an additional array added to the basic array. The basic array forms a basic area, and the additional array forms an additional area. The basic array includes at least three basic sub-arrays, and each basic sub-array forms a basic sub-area. The basic area includes a common area arranged in at least three basic sub-areas, and the common area is further arranged within the additional area.

In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed viewsfurther minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and usedor ignoredin product identification. A great variety of other features and arrangements are also detailed.

An input device includes a transparent layer having a top surface and a bottom surface, and an inner layer positioned below and directly contacting the bottom surface of the transparent layer, wherein the inner layer has a second index of refraction (n.sub.2) that is lower than a first index of refraction (n.sub.1) of the transparent layer, and wherein a first region of the transparent layer extends past an end of the inner layer. The device also includes a light source positioned below the bottom surface of the transparent layer, and a reflector arrangement configured to reflect light emitted by the light source into the transparent layer in or proximal to the first region of the transparent layer, wherein at least a portion of the light reflected into the transparent layer propagates within the transparent layer by total internal reflection.

Provided is a solid-state image sensor that includes a micro lens through which incident light is condensed, a photoelectrical conversion unit that generates electric charge based on the condensed incident light, and a translucent plate formed between the micro lens and the photoelectrical conversion unit and including a light-shielding wall provided between a translucent part provided for each pixel and the pixel. An antireflection film including films of two layers or more is formed between the light-shielding wall and the translucent part.

A system for visibility enhancement comprises a first sensor means comprising a camera adapted to record at least one image. A second sensor means is adapted to generate at least one position profile of at least one object located within a critical range of the first sensor means. An image processing means is adapted to receive a first input signal from the first sensor means containing the at least one image and a second input signal from the second sensor means containing the at least one position profile of the at least one object located within the critical range. The image processing means further manipulates the at least one image to generate a manipulated image by altering the contrast of that part of the image that shows the at least one object located within the critical range. A corresponding method of visibility enhancement is also disclosed.