Event recognition is one of the most active research areas in video surveillance fields. Advancement in event recognition systems mainly aims to provide convenience, safety and an efficient lifestyle for humanity. A precise, accurate and robust approach is necessary to enable event recognition systems to respond to sudden changes in various uncontrolled environments, such as the case of an emergency, physical threat and a fire or bomb alert. The performance of sudden event recognition systems depends heavily on the accuracy of low level processing, like detection, recognition, tracking and machine learning algorithms. This survey aims to detect and characterize a sudden event, which is a subset of an abnormal event in several video surveillance applications. This paper discusses the following in detail: (1) the importance of a sudden event over a general anomalous event; (2) frameworks used in sudden event recognition; (3) the requirements and comparative studies of a sudden event recognition system and (4) various decision-making approaches for sudden event recognition. The advantages and drawbacks of using 3D images from multiple cameras for real-time application are also discussed. The paper concludes with suggestions for future research directions in sudden event recognition.
Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter (SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.
Law enforcing authorities need to provide a scientific basis for the identification of any unknown individual. In recent years, dental records comparison has developed into one such credible method of confirming the identity of a deceased. This method is however restricted as dentists are not making and maintaining adequate records of their patients. Fortunately the advent of inexpensive cameras and print processing procedures has enabled the availability of ample antemortem photographs. Photographs in which a person expresses his/her teeth 'gleefully' has provided a sound scientific basis for the identification by comparing dental characteristics of the deceased.
The present conventional (destructive) method used in determining LAI is laborious, difficult and time consuming. Thus, an image-based measurement using camera system with fish eye lens offers an alternative means for an accurate indirect measurement of LAI in oil palm. In this study, a methodology was developed to improve the leaf area index of the oil palm determination using hemispherical photography as an indirect method. A set of true LAI data, collected using the destructive method, were used as a reference to calibrate the LAI measurements obtained by the hemispherical photography. A good relationship (r = 0.85) was found between age of palm and hemispherical photographic LAI. However, the estimated LAI obtained by the hemispherical photographic method was underestimated as compared to the destructive method. Some means of calibration was necessary to determine the relationship between the actual LAI and the hemispherical photographic LAI. It was necessary to multiply the LAI value from 5 years to 16 years, by a clumping factor of 2.14 for 5 to 9 year old palms, 2.33 for 10 to 14-year old palms and 2.37 for above 15- year old palms to calculate the accurate LAI values. For palms which are less than 5 year old (i.e. 2 to 3 years in this study), the photography LAI value was equal to the calculated LAI value. This proposed that correction factors would solve this underestimation effect. In addition, two equations were also proposed to estimate the true LAI from the Photographic LAI for immature and mature oil palm plantation.
Photovoice is an action-oriented qualitative method involving photography and story-telling. Although photovoice yields a powerful form of data that can be leveraged for research, intervention, and advocacy, it has arguably been underutilized within HIV research. Online, asynchronous photovoice methods represent a promising alternative to traditional in-person methods, yet their acceptability and feasibility with key populations and people living with HIV (PLWH) have yet to be explored. The current study describes the methods and evaluation of an online, asynchronous photovoice project conducted with 34 members of key populations and PLWH in Malaysia in 2021. A HIPAA-compliant website incorporating a series of instructional videos was created to facilitate participant engagement and data collection. Quantitative and qualitative indicators suggest that participants found the project to be highly acceptable and feasible. Online, asynchronous photovoice methods hold potential for increasing the scale of this powerful and versatile qualitative research method with key populations and PLWH.
Digital image forgery is becoming easier to perform because of the rapid development of various manipulation tools. Image splicing is one of the most prevalent techniques. Digital images had lost their trustability, and researches have exerted considerable effort to regain such trustability by focusing mostly on algorithms. However, most of the proposed algorithms are incapable of handling high dimensionality and redundancy in the extracted features. Moreover, existing algorithms are limited by high computational time. This study focuses on improving one of the image splicing detection algorithms, that is, the run length run number algorithm (RLRN), by applying two dimension reduction methods, namely, principal component analysis (PCA) and kernel PCA. Support vector machine is used to distinguish between authentic and spliced images. Results show that kernel PCA is a nonlinear dimension reduction method that has the best effect on R, G, B, and Y channels and gray-scale images.
The Philippines is home to the second largest known population of whale sharks in the world. The species is listed as endangered due to continued population declines in the Indo-Pacific. Knowledge about the connectivity within Southeast Asia remains poor, and thus international management is difficult. Here, we employed pop-up archival tags, data mining and dedicated effort to understand an aggregation of whale sharks at Honda Bay, Palawan, Philippines, and its role in the species' conservation. Between Apr and Oct 2018, we conducted 159 surveys identifying 117 individual whale sharks through their unique spot patterns (96.5% male, mean 4.5 m). A further 66 individual whale sharks were identified from local operators, and data mined on social media platforms. The satellite telemetry data showed that the whale sharks moved broadly, with one individual moving to Sabah, Malaysia, before returning to the site <1 year later. Similarly, another tagged whale shark returned to the site at a similar periodicity after reaching the Malay-Filipino border. One individual whale shark first identified in East Kalimantan, Indonesia by a citizen scientist was resighted in Honda Bay ~3.5 years later. Honda Bay is a globally important site for the endangered whale shark with connectivity to two neighbouring countries, highlighting the need for international cooperation to manage the species.
Choroidal osteoma is a benign ossifying tumor of the choroid, consisting of mature bone tissue. It has been described to enlarge and evolve at varying rates over time. Here, we report and quantify the progression of a unilateral choroidal osteoma in a 7-year-old boy by fundus photography, and document tumor remodeling by spectral domain optical coherence tomography images.
The proliferation of camera-trapping studies has led to a spate of extensions in the known distributions of many wild cat species, not least in Borneo. However, we still do not have a clear picture of the spatial patterns of felid abundance in Southeast Asia, particularly with respect to the large areas of highly-disturbed habitat. An important obstacle to increasing the usefulness of camera trap data is the widespread practice of setting cameras at non-random locations. Non-random deployment interacts with non-random space-use by animals, causing biases in our inferences about relative abundance from detection frequencies alone. This may be a particular problem if surveys do not adequately sample the full range of habitat features present in a study region. Using camera-trapping records and incidental sightings from the Kalabakan Forest Reserve, Sabah, Malaysian Borneo, we aimed to assess the relative abundance of felid species in highly-disturbed forest, as well as investigate felid space-use and the potential for biases resulting from non-random sampling. Although the area has been intensively logged over three decades, it was found to still retain the full complement of Bornean felids, including the bay cat Pardofelis badia, a poorly known Bornean endemic. Camera-trapping using strictly random locations detected four of the five Bornean felid species and revealed inter- and intra-specific differences in space-use. We compare our results with an extensive dataset of >1,200 felid records from previous camera-trapping studies and show that the relative abundance of the bay cat, in particular, may have previously been underestimated due to the use of non-random survey locations. Further surveys for this species using random locations will be crucial in determining its conservation status. We advocate the more wide-spread use of random survey locations in future camera-trapping surveys in order to increase the robustness and generality of inferences that can be made.
Anthropometry is defined as the scientific study of the measurements and proportions of the human body. To date, the most used methods for the acquisition of facial anthropometric parameters are direct method employing calipers and protractors tools, which are time-consuming, or indirect methods employing three-dimensional (3D) imaging systems, which are expensive. Despite the possible advantages of two-dimensional (2D) photography, it is not widely explored due to complications such as resolution and distortion of digital photos. The objective of this study is to
assess the accuracy of the Digital Single-Lens Reflector (DSLR) camera as an indirect method against direct method at different aperture and distance to subject. Adults aged 20-45 years were voluntarily recruited in this study (n=24). Twelve facial anthropometric parameters were measured for each participant using direct anthropometry (sliding caliper), and indirect anthropometry (DSLR camera). When placing the DSLR camera at 2.0 meters from subjects with f/6.3 aperture, nine facial anthropometric parameters were obtained accurately (p> .05). The findings suggested that
the accuracy of the DSLR camera as an indirect method for the acquisition of facial anthropometric parameters was established at the aperture setting of f/6.3 and the object distance at 2.0 meters. Therefore, it can be recommended as a facial anthropometry acquisition technique.
A photographic food atlas is a series of photographs showing different quantities of different foods. It serves as a portion size estimation aid (PSEA). In Malaysia, the existing food atlases, which display foods in exchanges and standard portion sizes, may not be representative of the actual sizes of the portions of food consumed by the local population. This paper aims to describe the development of a food atlas, namely the 'MY Food Album', and assess its usability as a PSEA. Thirty four participants (aged 31.6±20.9 y) served themselves, in a laboratory setting, what they considered to be typical, small, medium, and large portions of 23 amorphus food items. All food portions were weighed to obtain the mean and standard deviation of the range of food portion sizes to be displayed in the food atlas. Using standard camera and lighting settings, various local foods were photographed at an angle of 45º. A total of 393 food items were categorized into 14 food groups and presented as serial (n=101), guide (n=213) and range (n=79) photographs. The usability of MY Food Album was evaluated by six nutritionists and dietitians using an adapted questionnaire. The food atlas was perceived to be useful to aid in the quantification of food during dietary assessment. It was suggested that the function, dimension and application of fiducial markers be introduced in the food atlas to facilitate its use in size estimation. While MY Food Album was well-accepted as a PSEA, futher validation is required to evaluate the effectiveness of this newly developed food atlas in portion size estimation.
With only 5% of the world's wild tigers (Panthera tigris Linnaeus, 1758) remaining since the last century, conservationists urgently need to know whether or not the management strategies currently being employed are effectively protecting these tigers. This knowledge is contingent on the ability to reliably monitor tiger populations, or subsets, over space and time. In the this paper, we focus on the 2 seminal methodologies (camera trap and occupancy surveys) that have enabled the monitoring of tiger populations with greater confidence. Specifically, we: (i) describe their statistical theory and application in the field; (ii) discuss issues associated with their survey designs and state variable modeling; and, (iii) discuss their future directions. These methods have had an unprecedented influence on increasing statistical rigor within tiger surveys and, also, surveys of other carnivore species. Nevertheless, only 2 published camera trap studies have gone beyond single baseline assessments and actually monitored population trends. For low density tiger populations (e.g. <1 adult tiger/100 km(2)) obtaining sufficient precision for state variable estimates from camera trapping remains a challenge because of insufficient detection probabilities and/or sample sizes. Occupancy surveys have overcome this problem by redefining the sampling unit (e.g. grid cells and not individual tigers). Current research is focusing on developing spatially explicit capture-mark-recapture models and estimating abundance indices from landscape-scale occupancy surveys, as well as the use of genetic information for identifying and monitoring tigers. The widespread application of these monitoring methods in the field now enables complementary studies on the impact of the different threats to tiger populations and their response to varying management intervention.
BACKGROUND: More than 99% acne patients suffer from acne vulgaris. While diagnosing the severity of acne vulgaris lesions, dermatologists have observed inter-rater and intra-rater variability in diagnosis results. This is because during assessment, identifying lesion types and their counting is a tedious job for dermatologists. To make the assessment job objective and easier for dermatologists, an automated system based on image processing methods is proposed in this study.
OBJECTIVES: There are two main objectives: (i) to develop an algorithm for the enhancement of various acne vulgaris lesions; and (ii) to develop a method for the segmentation of enhanced acne vulgaris lesions.
METHODS: For the first objective, an algorithm is developed based on the theory of high dynamic range (HDR) images. The proposed algorithm uses local rank transform to generate the HDR images from a single acne image followed by the log transformation. Then, segmentation is performed by clustering the pixels based on Mahalanobis distance of each pixel from spectral models of acne vulgaris lesions.
RESULTS: Two metrics are used to evaluate the enhancement of acne vulgaris lesions, i.e., contrast improvement factor (CIF) and image contrast normalization (ICN). The proposed algorithm is compared with two other methods. The proposed enhancement algorithm shows better result than both the other methods based on CIF and ICN. In addition, sensitivity and specificity are calculated for the segmentation results. The proposed segmentation method shows higher sensitivity and specificity than other methods.
CONCLUSION: This article specifically discusses the contrast enhancement and segmentation for automated diagnosis system of acne vulgaris lesions. The results are promising that can be used for further classification of acne vulgaris lesions for final grading of the lesions.
KEYWORDS: acne grading; acne lesions; acne vulgaris; enhancement; segmentation
Understanding the factors influencing physical activity (PA) in the Asia-Pacific region is critical, given the high prevalence of inactivity in this area. The photovoice technique explores the types of PA and factors influencing PA among adolescents in Kuching, Sarawak. A total of 160 photographs were collected from participants (adolescents, n = 22, mean age = 14.27 ± 0.7 years, and parents, n = 8, mean age = 48 ± 6.8 years). Data analysis used constant comparison methods of a grounded theory. The Analysis Grid for Environments Linked to Obesity was used to categorize PA factors. Study findings were centered on the concept of safety, facilities, parental restriction, friends, cultural traits, media, community cohesiveness, and weather. The central theme was "feeling unsafe" when being outdoors. To promote PA behavior, provision of PA facilities needs to be supported by other programs that build on peer support, crime prevention, and traffic safety, together with other educational campaigns.
INTRODUCTION: This paper presents a comprehensive review of acne grading and measurement. Acne is a chronic disorder of the pilosebaceous units, with excess sebum production, follicular epidermal hyperproliferation, inflammation and Propionibacterium acnes activity. Most patients are affected with acne vulgaris, which is the prevalent type of acne. Acne vulgaris consists of comedones (whitehead and blackhead), papules, pustules, nodules and cysts.
OBJECTIVES: To review and identify the issues for acne vulgaris grading and computational assessment methods. To determine the future direction for addressing the identified issues.
METHODS: There are two main methods of assessment for acne severity grading, namely, lesion counting and comparison of patient with a photographic standard. For the computational assessment method, the emphasis is on computational imaging techniques.
RESULTS: Current acne grading methods are very time consuming and tedious. Generally, they rely on approximation for counting lesions and hence the assessment is quite subjective, with both inter and intra-observer variability. It is important to accurately assess acne grade to evaluate its severity as this influences treatment selection and assessment of response to therapy. This will further help in better disease management and more efficacious treatment.
CONCLUSION: Semi-automated or automated methods based on computational imaging techniques should be devised for acne grade assessment.
Many studies have shown that females smile more than males do in social situations. The present study extends this research by examining a large sample of high school yearbook photographs. In addition to assessing the degree of smiling, ratings were obtained of the following traits for each photograph: hair length, hair colour, masculine-feminine appearance and physical attractiveness. Results reconfirmed earlier research showing that females smile more than males do while they are being photographed. Other findings were that smiling was positively correlated with hair length, femininity and physical attractiveness for females but not for males. When a multivariate analysis was performed, none of these traits predicted smiling in males, and only femininity was significant in predicting smiling in females. Although social learning theories of smiling can account for some of these findings, a recently proposed neurohormonal theory seems to best explain why femininity is related to smiling in females but not in males.
Monitoring FAZ area enlargement enables physicians to monitor progression of the DR. At present, it is difficult to discern the FAZ area and to measure its enlargement in an objective manner using digital fundus images. A semi-automated approach for determination of FAZ using color images has been developed. Here, a binary map of retinal blood vessels is computer generated from the digital fundus image to determine vessel ends and pathologies surrounding FAZ for area analysis. The proposed method is found to achieve accuracies from 66.67% to 98.69% compared to accuracies of 18.13-95.07% obtained by manual segmentation of FAZ regions from digital fundus images.
To compare the measurements of the optic cup diameter with B-scan sonography with fundus photography in patients with clear ocular media and to propose a solution for the clinical problem of determining the cup-disc ratio in eyes with opaque ocular media.