Infrared Eye Image Research Articles

Effects of weaning and inactivated Lactobacillus helveticus supplementation on dairy calf behavioral and physiological indicators of affective state

The objectives of this study were to determine if weaning would induce behavioral and physiological indicators of a negative affective state, and if supplementation of inactivated Lactobacillus helveticus (ILH) to dairy calves would reduce those indicators of negative affect during weaning. Male Holstein calves (n = 23) were enrolled in the study on d 1 of life. The calves were housed in individual pens in 1 of 4 rooms for the 42 d study. Calves began a stepdown weaning from 9 L/d of milk replacer (MR), at 150 g of MR powder/L, on d 35 and received 6 L/d on d 35 - 36, 3 L/d on d 37 - 38, and 0.4 L/d on d 39 - 42. The MR was divided between 3 meals/d until the last 0.4 L/d phase which was divided between 2 meals/d. Calves had ad libitum water access throughout the study and calf starter from d 28 onwards. Within room, calves were assigned to 1 of 2 treatments: 1) control (CON; n = 11) and 2) 5 g of ILH/d split over and mixed into the 0800 h and 2000 h milk feedings from d 3-42 (ILH; n = 12). Lying behavior was recorded using HOBO data loggers from d 21-41. On d 33, 37 and 41, infrared eye images were taken to determine maximum eye temperature (MET), saliva samples were collected to determine cortisol concentration, and play assessments were conducted to quantify play behavior. On d 34, 38, and 42, blood samples were collected to determine blood serotonin concentration, whereas on d 38 and 39, calves were tested with a cognitive task. A subset of calves (n = 5/treatment) were euthanized to collect gut and brain tissue samples for serotonin concentration on d 43. Weaning resulted in fewer (d 37-41, tendency: d 36), but longer (d 38-41, tendency: d 37), lying bouts and reduced play (d 41), although no changes in lying time, MET, saliva cortisol, nor blood serotonin were detected with initiation of weaning. Supplementation of ILH was associated with lower lying time throughout the study, and reduced play duration and higher salivary cortisol and MET during weaning. No differences in lying bouts, play count, blood and tissue (colon, ileum, prefrontal cortex and brain stem) serotonin concentration, and time to complete the cognitive task were detected between the treatments. Overall, weaning induced behavioral changes indicative of negative affective state, and some behavioral differences were observed with ILH supplementation both before and during weaning, with some physiological changes observed during weaning.

적외선 눈 영상 특징을 통한 용접면 착용자의 시각피로도 측정에 대한 연구

적외선 눈 영상 특징을 통한 용접면 착용자의 시각피로도 측정에 대한 연구

MTCD: Cataract detection via near infrared eye images

Globally, cataract is a common eye disease and one of the leading causes of blindness and vision impairment. The traditional process of detecting cataracts involves eye examination using a slit-lamp microscope or ophthalmoscope by an ophthalmologist, who checks for clouding of the normally clear lens of the eye. The lack of resources and unavailability of a sufficient number of experts pose a burden to the healthcare system throughout the world, and researchers are exploring the use of AI solutions for assisting the experts. Inspired by the progress in iris recognition, in this research, we present a novel algorithm for cataract detection using near-infrared eye images. The NIR cameras, which are popularly used in iris recognition, are of relatively low cost and easy to operate compared to ophthalmoscope setup for data capture. However, such NIR images have not been explored for cataract detection. We present deep learning-based eye segmentation and multitask network classification networks for cataract detection using NIR images as input. The proposed segmentation algorithm efficiently and effectively detects non-ideal eye boundaries and is cost-effective, and the classification network yields very high classification performance on the cataract dataset.

Experimental Verification of Objective Visual Fatigue Measurement Based on Accurate Pupil Detection of Infrared Eye Image and Multi-Feature Analysis

As the use of electronic displays increases rapidly, visual fatigue problems are also increasing. The subjective evaluation methods used for visual fatigue measurement have individual difference problems, while objective methods based on bio-signal measurement have problems regarding motion artifacts. Conventional eye image analysis-based visual fatigue measurement methods do not accurately characterize the complex changes in the appearance of the eye. To solve this problem, in this paper, an objective visual fatigue measurement method based on infrared eye image analysis is proposed. For accurate pupil detection, a convolutional neural network-based semantic segmentation method was used. Three features are calculated based on the pupil detection results: (1) pupil accommodation speed, (2) blink frequency, and (3) eye-closed duration. In order to verify the calculated features, differences in fatigue caused by changes in content color components such as gamma, color temperature, and brightness were compared with a reference video. The pupil detection accuracy was confirmed to be 96.63% based on the mean intersection over union. In addition, it was confirmed that all three features showed significant differences from the reference group; thus, it was verified that the proposed analysis method can be used for the objective measurement of visual fatigue.

Gaze-in-wild: A dataset for studying eye and head coordination in everyday activities

The study of gaze behavior has primarily been constrained to controlled environments in which the head is fixed. Consequently, little effort has been invested in the development of algorithms for the categorization of gaze events (e.g. fixations, pursuits, saccade, gaze shifts) while the head is free, and thus contributes to the velocity signals upon which classification algorithms typically operate. Our approach was to collect a novel, naturalistic, and multimodal dataset of eye + head movements when subjects performed everyday tasks while wearing a mobile eye tracker equipped with an inertial measurement unit and a 3D stereo camera. This Gaze-in-the-Wild dataset (GW) includes eye + head rotational velocities (deg/s), infrared eye images and scene imagery (RGB + D). A portion was labelled by coders into gaze motion events with a mutual agreement of 0.74 sample based Cohen’s κ. This labelled data was used to train and evaluate two machine learning algorithms, Random Forest and a Recurrent Neural Network model, for gaze event classification. Assessment involved the application of established and novel event based performance metrics. Classifiers achieve ~87% human performance in detecting fixations and saccades but fall short (50%) on detecting pursuit movements. Moreover, pursuit classification is far worse in the absence of head movement information. A subsequent analysis of feature significance in our best performing model revealed that classification can be done using only the magnitudes of eye and head movements, potentially removing the need for calibration between the head and eye tracking systems. The GW dataset, trained classifiers and evaluation metrics will be made publicly available with the intention of facilitating growth in the emerging area of head-free gaze event classification.

HEYEbrid

We introduce hEYEbrid, a calibration-free method for spontaneous and long-term eye gaze tracking, with competitive gaze estimation. It is based on a hybrid concept that combines infrared eye images with corneal imaging. For this, two eye cameras are mounted on a glasses frame. In this way, the pupil can be tracked quickly with high precision. This information is translated into the corneal image, which is used to create a connection to the environment, acting like a scene camera. In a user study with 20 participants, we evaluated our approach against an extended version of the system, called 3C-hEYEbrid, and a state-of-the-art head-mounted Pupil Labs eye tracker. We show that hEYEbrid provides accurate gaze estimation in unconstrained environments and is robust against calibration drift (e.g. caused by taking off and putting on the device). In addition, we present a mobile and wearable implementation of hEYEbrid and 3C-hEYEbrid, that is also usable with a monocular Pupil Labs eye tracker. It connects the head-mounted device to a mobile phone, enabling gaze estimation in real time. hEYEbrid represents a significant step towards pervasive gaze-based interfaces.

Pupil localization algorithm combining convex area voting and model constraint

Locating the center of the eyes plays a significant role in many computer vision applications and research, such as face alignment, face recognition, human-computer interaction, control devices for disabled people, user attention and gaze estimation. The disturbances such as occlusions by eyelashes or eyelids, uneven spots and spectacle frames of glasses affect the accuracy and stability of eye center location. This paper presents a hybrid eye center locating methodology for infrared eye images. The pupil edge points are extracted by Starburst algorithm, and when we get the position and the gradient of the edge points, the approximate pupil boundary is determined by a convex region voting methods. After that, the boundary edge points are iteratively optimized by fitting an ellipses modeling constraint. Finally, the pupil is located correctly. Experiment shows that this algorithm has performance advantages compared with some state of the art approaches in pupil localization accuracy, iteration times and their performance. This algorithm combining convex area voting and model constraint has strong robustness, high accuracy and speed in real environments with occlusions and distortion pupil.

CNN-Based Pupil Center Detection for Wearable Gaze Estimation System

This paper presents a convolutional neural network- (CNN-) based pupil center detection method for a wearable gaze estimation system using infrared eye images. Potentially, the pupil center position of a user’s eye can be used in various applications, such as human-computer interaction, medical diagnosis, and psychological studies. However, users tend to blink frequently; thus, estimating gaze direction is difficult. The proposed method uses two CNN models. The first CNN model is used to classify the eye state and the second is used to estimate the pupil center position. The classification model filters images with closed eyes and terminates the gaze estimation process when the input image shows a closed eye. In addition, this paper presents a process to create an eye image dataset using a wearable camera. This dataset, which was used to evaluate the proposed method, has approximately 20,000 images and a wide variation of eye states. We evaluated the proposed method from various perspectives. The result shows that the proposed method obtained good accuracy and has the potential for application in wearable device-based gaze estimation.

Iris segmentation for visible wavelength and near infrared eye images

State-of-the-art iris segmentation algorithms exhibit poor performance for non-ideal data, which is mainly because of the noise such as low contrast, non-uniform illumination, reflections, and among others. To address this issue, a robust iris segmentation scheme is proposed that includes the following: First, a set of the Seed-pixels in a preprocessed eye image is marked adaptively. Next, a two-fold scheme based on a Circu-differential accumulator (CDA) and gray statistics is adopted to localize coarse iris region robustly. Notably, the proposed CDA has close resemblance with the Hough transform; however, it consumes relatively less memory and is free from thresholding as well. Similarly, pupillary boundary is localized, which is verified through an intensity test as well. Next, a refine estimate for the limbic boundary is extracted. After that, iris boundaries are regularized using the Fourier series. Finally, the eyelids are localized using a Para-differential accumulator (PDA), and eyelashes and reflections are also localized adaptively in the polar form of iris. Experimental results on the near infrared (NIR) and visible wavelength (VW) iris databases show that the proposed technique outperforms contemporary approaches.

Changes in the ocular saccade kinematics after a seven-day dry immersion

To assess the effects of long-term support unload on gaze control, five subjects were tested for the successful touch of a light target unpredictably emerging in the peripheral field of vision before and immediately after a seven-day dry immersion. The test did not set time requirements on gaze fixation on the target or motor task implementation. Ocular movements were recorded with an infrared eye image analyzer at 100 Hz. Modification of the dependences of the maximum velocity and duration of a saccade towards a homolateral target at the amplitude following immersion pointed to the speeding-up of the saccadic eye movements.

Vision Chip Architecture for Detecting Line of Sight Including Saccade

Rapid eye motion, or so called saccade, is a very quick eye motion which always occurs regardless of our intention. Although the line of sight (LOS) with saccade tracking is expected to be used for a new type of computer-human interface, it is impossible to track it using the conventional video camera, because of its speed which is often up to 600 degrees per second. Vision Chip is an intelligent image sensor which has the photo receptor and the image processing circuitry on a single chip, which can process the acquired image information by keeping its spatial parallelism. It has also the ability of implementing the very compact integrated vision system. In this paper, we describe the vision chip architecture which has the capability of detecting the line of sight from infrared eye image, with the processing speed supporting the saccade tracking. The vision chip described here has the pixel parallel processing architecture, with the node automata for each pixel as image processing. The acquired image is digitized to two flags indicating the Purkinje's image and the pupil by comparators at first. The digitized images are then shrunk, followed by several steps of expanding by node automata located at each pixel. The shrinking process is kept executed until all the pixels disappear, and the pixel disappearing at last indicates the center of the Purkinje's image and the pupil. This disappearing step is detected by the projection circuitry in pixel circuit for fast operation, and the coordinates of the center of the Purkinje's image and the pupil are generated by the simple encoders. We describe the whole architecture of this vision chip, as well as the pixel architecture. We also describe the evaluation of proposed algorithm with numerical simulation, as well as processing speed using FPGA, and improvement in resolution using column parallel architecture.