An artificial neural network-based method for selecting a surface type of an object includes receiving at least one object image, performing surface type identification on each of the at least one object image by using a first predictive model to categorize the object image to one of a first normal group and a first abnormal group, and performing surface type identification on each output image in the first normal group by using a second predictive model to categorize the output image to one of a second normal group and a second abnormal group.

An artificial neural network-based method for detecting a surface pattern of an object includes receiving a plurality of object images, dividing each object image into a plurality of image areas, designating at least one region of interest from the plurality of image areas of each of the object images, and performing deep learning with the at least one region of interest to build a predictive model for identifying a surface pattern of the object.

An artificial neural network-based method for selecting a surface type of an object is suitable for selecting a plurality of objects. The artificial neural network-based method for selecting a surface type of an object includes performing surface type identification on a plurality of object images by using a plurality of predictive models to obtain a prediction defect rate of each of the predictive models, wherein the object images correspond to surface types of a part of the objects, and cascading the predictive models according to the respective prediction defect rates of the predictive models into an artificial neural network so as to select the remaining objects.

An artificial neural network-based method for selecting a surface type of an object is suitable for selecting a plurality of objects. The artificial neural network-based method for selecting a surface type of an object includes performing surface type identification on a plurality of object images by using a plurality of predictive models to obtain a prediction defect rate of each of the predictive models, wherein the object images correspond to surface types of a part of the objects, and cascading the predictive models according to the respective prediction defect rates of the predictive models into an artificial neural network so as to select the remaining objects.

A system for detecting a surface type of an object includes a driver component, a driver component, and a plurality of photosensitive elements. The surface of the object is divided along a first direction into a plurality of areas, and the driver component sequentially moves one of the plurality of areas to a detection position. The light source component faces the detection position and provides light of a plurality of spectra that are different from one another to illuminate the detection position. The photosensitive elements face different sections of the area at the detection position, to capture detection images of different sections of the area located at the detection position under the light of each of the spectra. One photosensitive axis of the photosensitive elements is parallel to the normal line while another photosensitive axis of the photosensitive elements is between the normal line and the first direction.

A system for detecting a surface type of an object includes a driver component, a driver component, and a plurality of photosensitive elements. The surface of the object is divided along a first direction into a plurality of areas, and the driver component sequentially moves one of the plurality of areas to a detection position. The light source component faces the detection position and provides light of a plurality of spectra that are different from one another to illuminate the detection position. The photosensitive elements face different sections of the area at the detection position, to capture detection images of different sections of the area located at the detection position under the light of each of the spectra. One photosensitive axis of the photosensitive elements is parallel to the normal line while another photosensitive axis of the photosensitive elements is between the normal line and the first direction.

Disclosed are systems and methods for clinical trial assessment of skin disease treatment. The disclosure includes obtaining a series of digital images over a period of time, wherein each digital image includes an affected area of the subject; identifying characteristic morphologies and lesions in the affected area of the subject in each of the digital images; classifying each of the detected and segmented morphologies and lesions into one or more identified categories for each of the digital images; assigning a global score to each of the digital images based on a count of the detected and segmented characteristic morphologies and lesions in each of the one or more identified categories; analyzing the global scores of each of the digital images; and making an assessment of the clinical trial based on the analysis of the global scores of each of the digital images.

Embodiments include apparatus for predicting cancer recurrence based on local co-occurrence of cell morphology (LoCoM). The apparatus includes image acquisition circuitry that identifies and segments at least one cellular nucleus represented in an image of a region of tissue demonstrating cancerous pathology; local nuclei graph (LNG) circuitry that constructs an LNG based on the at least one cellular nucleus, and computes a set of nuclear morphology features for a nucleus represented in the LNG; LoCoM circuitry that constructs a co-occurrence matrix based on the nuclear morphology features, computes a set of LoCoM features for the co-occurrence matrix, and computes a LoCoM signature for the image based on the set of LoCoM features; progression circuitry that generates a probability that the region of tissue will experience cancer progression based on the LoCoM signature, and classifies the region of tissue as a progressor or non-progressor based on the probability.

Embodiments include apparatus for predicting cancer recurrence based on local co-occurrence of cell morphology (LoCoM). The apparatus includes image acquisition circuitry that identifies and segments at least one cellular nucleus represented in an image of a region of tissue demonstrating cancerous pathology; local nuclei graph (LNG) circuitry that constructs an LNG based on the at least one cellular nucleus, and computes a set of nuclear morphology features for a nucleus represented in the LNG; LoCoM circuitry that constructs a co-occurrence matrix based on the nuclear morphology features, computes a set of LoCoM features for the co-occurrence matrix, and computes a LoCoM signature for the image based on the set of LoCoM features; progression circuitry that generates a probability that the region of tissue will experience cancer progression based on the LoCoM signature, and classifies the region of tissue as a progressor or non-progressor based on the probability.

An image processing device which is capable of accurately detect pixels covered by cloud shadows and remove effects of the cloud shadows in an images are provided. The device includes: a cloud transmittance calculation unit that calculates transmittance of the one or more clouds in an input image, for each pixel; a cloud height estimation unit that determines estimation of a height from the ground to each cloud in the input image to detect position of corresponding one or more shadows; an attenuation factor estimation unit that calculates attenuation factors for the direct sun irradiance by applying an averaging filter to the cloud transmittance calculated; and a shadow removal unit that corrects pixels affected by the one or more shadows, based on a physical model of a cloud shadow formation by employing the attenuation factors calculated and the position, and outputs an image which includes the pixels corrected.