Abstract: A tag hanger has a strap which can pass around a support structure, such as a D-ring on an animal collar, and a retainer assembly that clamps one or more tags to one end of the strap, restraining their motion to prevent noise caused by the tags jangling together. The other end of the strap attaches to the retainer assembly to secure the tag holder to the support structure. A blocking element can be included on the strap to prevent contact between the tags and the support structure. The retainer assembly can employ a hex-head bolt that serves as a base element and a threaded retainer shaft that passes through a retainer passage in the strap and through hanger passages in the tags; a nut threadably engaging the bolt can then serve as a clamping element to secure the tags to the strap.

Abstract: A camera system may include an image sensor to generate real-time image data of a scene having a subject. A pose evaluator can generate a pose metric signal having a pose value that provides a variable measure of a pose quality for the subject in the scene. A pose feedback indicator can provide user-perceptible feedback demonstrating the value of the pose metric signal, such that the variable measure of the pose quality is provided.

Abstract: A platform assembly has a rigid support with an array of threaded passages extending therethrough; threaded posts are engaged in the threaded passages and extend above the rigid support by a distance adjusted by rotation of each threaded post in its associated threaded passage. Manually-adjusted dog point screws can provide the threaded posts, and self-locking nuts can provide the threaded passages. A platform of smooth, slightly flexible material extends over the threaded posts and has an array of mounting elements that magnetically attach to the threaded posts to hold the platform tightly against the end of each post. Adjusting the positions of the threaded posts serves to adjust the precise position and flatness of the platform surface relative to the rigid support, and with respect to a print head of a 3D printer in which the rigid support is incorporated.

Abstract: Systems and methods of smile detection are disclosed. An exemplary method comprises generating a search map (400) for a subset of an image (300). The method also comprises identifying a plurality of candidates (400a-f) representing mouth corners. The method also comprises generating parabolas (410) between each pair of candidates representing mouth corners. The method also comprises analyzing contour of at least one of the parabolas to determine whether the mouth curves substantially upward to form a smile or curves substantially downward to form a frown.

Abstract: A device to apply detection schemes to texture information of a face detected within an image to generate mouth corner candidates and identify best matching mouth corners by applying a geometric model to the moth corner candidates.

Abstract: Devices and methods for automatic monitoring of fluid of a patient are disclosed, comprising a patient line, a transfer disk which receives the fluid and controllably transfers the fluid to test substrates, and a sensor disk which houses the test substrates. The sterile transfer disk may be configured to maintain the sterility of the patient sampling assembly while transferring samples to non-sterile components, such as the sensor disk.

Abstract: Devices and methods for automatic monitoring of fluid of a patient are disclosed, comprising a patient line, a transfer disk which receives the fluid and controllably transfers the fluid to test substrates, and a sensor disk which houses the test substrates. The sterile transfer disk may be configured to maintain the sterility of the patient sampling assembly while transferring samples to non-sterile components, such as the sensor disk.

Abstract: An image contains a representation of a person's face, where the image has plural points each comprising multiple components of a color space. For each of the plural points, at least two of the color space components are combined to produce a respective aggregate value. The image is processed to convert at least some of the points of the image based on the calculated aggregate values.

Abstract: Face-detection processing methods, image processing devices, and articles of manufacture are described. According to one arrangement, a face-detection processing method includes accessing image data of a plurality of images to be processed for detection of human faces in the images, determining whether or not to use skin-detection processing for face-detection processing of individual ones of the images, and in accordance with the determining, performing the face-detection processing of one of the images using the skin-detection processing to detect human faces in the one of the images and performing the face-detection processing of another of the images without using the skin-detection processing to detect human faces in the another of the images.

Abstract: Systems and methods of smile detection are disclosed. An exemplary method comprises generating a search map (400) for a subset of an image (300). The method also comprises identifying a plurality of candidates (400a-f) representing mouth corners. The method also comprises generating parabolas (410) between each pair of candidates representing mouth corners. The method also comprises analyzing contour of at least one of the parabolas to determine whether the mouth curves substantially upward to form a smile or curves substantially downward to form a frown.

Abstract: Systems, methods, and other embodiments associated with increasing face detection speed are described. One example method includes determining whether to control a face detection process to selectively perform a face detection in a patch in a digital image. The face detection may be based, at least in part, on determining whether the patch overlaps a face previously identified by the face detection process. The example method may also include providing a signal to control the face detection process to perform the face detection upon determining that a patch overlap does not exceed an overlap factor.

Abstract: Systems and methods are disclosed that determine a largest patch size to traverse a digital image, analyze the digital image to detect one or more first objects of a size approximately the same as the largest patch size, and discontinue analyzing the digital image when the digital image includes the first object(s) of a size approximately the same as the largest patch size. The patch size is decremented to progressively smaller patch sizes if the first object(s) of a size approximately the same as the largest patch size is not detected and the digital image is further analyzed to detect one or more first objects of a size approximately the same as the smaller patch size until the first object(s) are detected or the patch size is decremented below a predetermined smallest size.

Abstract: A device to apply detection schemes to texture information of a face detected within an image to generate mouth corner candidates and identify best matching mouth corners by applying a geometric model to the moth corner candidates.

Abstract: An on-vehicle disk brake lathe has a motor connected to a right-angle gearbox mounted to a body of the lathe, the gearbox in turn driving a spindle shaft through a flexible drive linkage such as a belt or chain. The spindle shaft extends parallel to a gearbox output shaft, and both are normal to an axis of rotation of the motor. The flexible drive linkage can be tensioned by adjustably mounting the gearbox to the lathe body or by use of an adjustably positioned tensioning element. A cover can enclose the flexible drive linkage. The separate gearbox allows the use of durable bearings for the spindle shaft, and allows these bearings to be spaced apart to provide a high degree of stability. The modular structure of the resulting lathe simplifies fabrication and repair, and allows use of a modular body for the lathe.

Abstract: A camera system may include an image sensor to generate real-time image data of a scene having a subject. A pose evaluator can generate a pose metric signal having a pose value that provides a variable measure of a pose quality for the subject in the scene. A pose feedback indicator can provide user-perceptible feedback demonstrating the value of the pose metric signal, such that the variable measure of the pose quality is provided.

Abstract: A face is detected within a series of imaging frames. One or more changes to a facial feature of the face are detected in progressive frames of the series. The face is identified based on the detected changes.

Abstract: An image contains a representation of a person's face, where the image has plural points each comprising multiple components of a color space. For each of the plural points, at least two of the color space components are combined to produce a respective aggregate value. The image is processed to convert at least some of the points of the image based on the calculated aggregate values.

Abstract: Face-detection processing methods, image processing devices, and articles of manufacture are described. According to one arrangement, a face-detection processing method includes accessing image data of a plurality of images to be processed for detection of human faces in the images, determining whether or not to use skin-detection processing for face-detection processing of individual ones of the images, and in accordance with the determining, performing the face-detection processing of one of the images using the skin-detection processing to detect human faces in the one of the images and performing the face-detection processing of another of the images without using the skin-detection processing to detect human faces in the another of the images.

Abstract: Devices and methods for automatic monitoring of fluid of a patient are disclosed, comprising a patient line, a transfer disk which receives the fluid and controllably transfers the fluid to test substrates, and a sensor disk which houses the test substrates. The sterile transfer disk may be configured to maintain the sterility of the patient sampling assembly while transferring samples to non-sterile components, such as the sensor disk.

Abstract: Systems and methods are disclosed that determine a largest patch size to traverse a digital image, analyze the digital image to detect one or more first objects of a size approximately the same as the largest patch size, and discontinue analyzing the digital image when the digital image includes the first object(s) of a size approximately the same as the largest patch size. The patch size is decremented to progressively smaller patch sizes if the first object(s) of a size approximately the same as the largest patch size is not detected and the digital image is further analyzed to detect one or more first objects of a size approximately the same as the smaller patch size until the first object(s) are detected or the patch size is decremented below a predetermined smallest size.