Find research datasets worth reusing

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 5. Sample Image data 2

It helps to write our code in C# and to make an application in dot net framework, which collects facial images using a webcam/or other video grabbing tools. Then it implements Haar detection to extract facial features and to draw image pattern for matching both images.   After image matching, we got a positive result at 93% times, for 1000 random sample images tested on the nine criteria of orientation.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 3. The methodology flowchart

The methodology of our experimental method is described in Figure 3 below. It helps to write our code in C# and to make an application in dot net framework, which collects facial images using a webcam/or other video grabbing tools. Then it implements Haar detection to extract facial features and to draw image pattern for matching both images.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 4. Sample image data 1

After image matching, we got a positive result at 93% times, for 1000 random sample images tested on the nine criteria of orientation.  After matching the images with the reference image, it gets the nearest orientation matches and they could be Font left, Font right, Down-left, Down Right, Up left, Upright, Font Straight, Up Straight, Down Straight. Initially, some constraints must be satisfied to realize a successful correct matching. The facial regions, concerned on eyes and nose points, have the following characteristic: if there is almost one missing point for the region of the same type then the comparison will be performed. There must be the same number of feature points for both eyes and nose separately. If this condition is satisfied then a new comparison will be performed.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 2. A Sample Image from extracted feature

Using these data, it creates a new picture and uses these data as a starting point for drawing. By using the data, it gets a model and shape of face without color and facial expression (Gourier et al.; 2004), such as Figure 2. It got a model of faces using these features.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 1. Face area detection

The first step in facial feature detection is detecting the face. This requires analyzing the entire image. The second step is using the isolated face(s) to detect each feature. The result is shown in Figure 1. Since each portion of the image used to detect a feature is much smaller than that of the whole image, detection of all three facial features takes less time on average than detecting the face itself. Using a 1.2GHz AMD processor to analyze a 320 by 240 image, a frame rate of 3 frames per second was achieved. Since a frame rate of 5 frames per second was achieved in facial detection only by using a much faster processor, regionalization provides a tremendous increase in efficiency in facial feature detection.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 5. Sample Image data 2

After image matching, we got a positive result at 93% times, for 1000 random sample images tested on the nine criteria of orientation.  Face orientation recognition is an important topic in computer vision and pattern recognition. Due to the non-rigid properties of faces, it is computationally expensive and difficult to achieve good recognition accuracy and robustness in face orientation recognition. In this paper, we propose an image mapping technique for face analysis in smart camera networks with a feature extraction and data from the facial feature. We estimate the face orientation angles in all camera views, based on the matched imaged data. Our objective is to obtain a set of facial structures which can work as landmarks for tracking and recognition of facial expressions.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 4. Sample image data 1

After matching the images with the reference image, it gets the nearest orientation matches and they could be Font left, Font right, Down-left, Down Right, Up left, Upright, Font Straight, Up Straight, Down Straight. Initially, some constraints must be satisfied to realize a successful correct matching. The facial regions, concerned on eyes and nose points, have the following characteristic: if there is almost one missing point for the region of the same type then the comparison will be performed. There must be the same number of feature points for both eyes and nose separately. If this condition is satisfied then a new comparison will be performed.  After image matching, we got a positive result at 93% times, for 1000 random sample images tested on the nine criteria of orientation.

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 1. Face area detection

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 3. The methodology flowchart

BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 2. A Sample Image from extracted feature

opencc-by-4.0Apr 2018View details →

Quantitative susceptibility mapping of articular cartilage: ex vivo findings at multiple orientations and following different degradation treatments

This dataset contains all the raw source data and MATLAB analysis functions that comprise the study: Quantitative susceptibility mapping of articular cartilage: Ex vivo findings at multiple orientations and following different degradation treatments Magnetic Resonance in Medicine | DOI: 10.1002/mrm.27216 Nykänen Olli(1*), Rieppo Lassi(2,3), Töyräs Juha(1,4), Kolehmainen Ville(1), Saarakkala Simo(2,3,5), Shmueli Karin(6) and Nissi Mikko Johannes(1) (1) Department of Applied Physics, University of Eastern Finland, POB 1627, FI-70211 Kuopio, Finland (2) Research Unit of Medical Imaging, Physics and Technology, University of Oulu, POB 5000, FI-90014 Oulu, Finland (3) Medical Research Center Oulu, Oulu University Hospital and University of Oulu, Oulu, Finland (4) Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland (5) Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland (6) Department of Medical Physics & Biomedical Engineering, University College London(UCL), London, United Kingdom *Corresponding author: Olli Nykänen Department of Applied Physics, University of Eastern Finland POB 1627 FI-70211, Kuopio, Finland olli.nykanen@uef.fi +358-50-5556357 Keywords: cartilage, collagen matrix, quantitative susceptibility mapping, MRI, osteoarthritis Included folders and files are: - article_figures: all figures published in the manuscript - data: all MRI, histological, and PLM data used in this article - matlab_functions: matlab functions used in data analysis with subfolders:     - aedes_plugins: plugins for aedes (http://aedes.uef.fi) for calculation of QS- and T2* maps     - fitting_functions: functions for fitting relaxation times or TKD-method for QSM, used by the functions in above folder     - miscellaneous_functions: small helper functions for a number of small tasks utilized by the other scripts and functions - ReadMe.txt: this file Notes for setting up Aedes correctly for this dataset: Run Aedes -> Tools -> Edit VNMR Defaults:   - Return: FT + K-space   - DC: off   - Zeropadding: off   - Sorting & fastread: on   - Precision: single   - Read_fcn: readvnmr   - Orient: no See more info in separate readme files included in each folder. (Olli Nykänen, Apr 17, 2018)

opencc-by-4.0Apr 2018View details →

Supplementary Information for: Quantifying the potential for consumer-oriented policy to reduce domestic and foreign carbon emissions

These files comprise the Supplementary Information for the paper "Quantifying the potential for consumer-oriented policy to reduce domestic and foreign carbon emissions" submitted to Climate Policy.

opencc-zeroDec 2009View details →

FIGURE 2 in Four new species of Nanocladius Kieffer from Oriental China (Diptera: Chironomidae: Orthocladiinae)

FIGURE 2. Nanocladius (N.) calvatus sp. n., male. A — wing. B — tergites I, III – VII. C — hypopygium, dorsal view. D — hypopygium, ventral view. E — inferior volsella.

opencc-by-4.0Jan 2019View details →

In-house high energy remote SAD-phasing using the magic triangle: how to tackle the P1 low symmetry using multiple orientations on the same human IBA57 crystal to increase multiplicity.

The dataset named IBA57-I3C.zip contains pck diffraction images of 9 runs (orientations) of a human IBA57 crystal soaked with 5-amino-2,4,6-triiodoisophthalic acid (I3C) collected on an in-house source. Multiple orientations (runs) of the very same triclinic crystal have been exploited to acquire sufficient real data multiplicity for SAD-phasing. Each folder named run* contains the pck images and the relevant XDS.INP file for processing. The file runs.txt in the top directory gives the phi, kappa, omega and theta details on each of the 9 runs. The dataset named IBA57-native.zip contains pck images of 1 run (360 images around phi only) of a native human IBA57 crystal collected on the same in-house source and the relevant XDS.INP file for processing; this dataset is needed for SIRAS along with the I3C dataset.

opencc-by-4.0Jul 2019View details →

2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy

General This dataset consists out of multiple Second Harmonic Generation (SHG) microscopy scans of collagen fibers in mice bones. Some mices are diseased with osteogenesis imperfecta (brittle bone). We used this data to investigate the segmentation of uncertain local collagen fiber orientations. The corresponding paper "2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy" is accepted at GCPR 2019. Abstract Collagen fiber orientations in bones, visible with Second Harmonic Generation (SHG) microscopy, represent the inner structure and its alteration due to influences like cancer. While analyses of these orientations are valuable for medical research, it is not feasible to analyze the needed large amounts of local orientations manually. Since we have uncertain borders for these local orientations only rough regions can be segmented instead of a pixel-wise segmentation. We analyze the effect of these uncertain borders on human performance by a user study. Furthermore, we compare a variety of 2D and 3D methods such as classical approaches like Fourier analysis with state-of-the-art deep neural networks for the classification of local fiber orientations. We present a general way to use pretrained 2D weights in 3D neural networks, such as Inception-ResNet-3D a 3D extension of Inception-ResNet-v2. In a 10 fold cross-validation our two stage segmentation based on Inception-ResNet-3D and transferred 2D ImageNet weights achieves a human comparable accuracy. Links A preprint of the paper is available at <a href="https://arxiv.org/abs/1907.12868">https://arxiv.org/abs/1907.12868</a>. The final publication is available at Springer via <a href="https://doi.org/10.1007/978-3-030-33676-9_26">https://doi.org/10.1007/978-3-030-33676-9_26</a> The source code is available at <a href="https://github.com/Emprime/uncertain-fiber-segmentation">https://github.com/Emprime/uncertain-fiber-segmentation</a>. Data description Please read the accompanying paper for more information about the dataset. Please see the source code for more information about the usage of the data. <ul> <li>shg-ce-de:  contains the enhanced and denoised scans as image slices, the scans are sorted by mice (wt wildtyp, het ill mice), scan location and individual scan</li> <li>shg-masks: contains the ground truth masks for the three different classes (similar - Green, dissimilar - Red, not of interest - blue)</li> <li>shg-featues: contains the input and gt for the second stage of the proposed two stage segmentation</li> <li>shg-cross-splits: contains the 10 random splits for the 10 fold cross validation</li> <li>logs-prediction: contains the 10 tensorboard logs, weights and predictions for the 10 fold cross validations</li> </ul>

Fig. 6. Neopanorpa lungtaushana Cheng, 1957. A, C–I. Male. A. Habitus, dorsal view. C. Head, frontal view. D. T3 and T4 in Taxonomy of the genus Neopanorpa van der Weele, 1909 (Mecoptera, Panorpidae) from the Oriental Region, with the description of two new species

Fig. 6. Neopanorpa lungtaushana Cheng, 1957. A, C–I. Male. A. Habitus, dorsal view. C. Head, frontal view. D. T3 and T4, left-lateral view. E. Epandrium and hypandrium, right-lateral view. F–G. Genital bulb, ventral and dorsal views, respectively. H–I. Aedeagal complex, ventral and rightlateral views, respectively. – B, J–L. Female. B. Habitus, dorsal view. J. Subgenital plate, ventral view. K–L. Medigynium, right-lateral and ventral views, respectively.

Fig. 4 in Taxonomy of the genus Neopanorpa van der Weele, 1909 (Mecoptera, Panorpidae) from the Oriental Region, with the description of two new species

Fig. 4. Neopanorpa ocellaris (Navás, 1908), living female. The female is feeding on a dead crane fly. Photo by Wei-Liang Xie from Huanjiang County, Guangxi Province, China.

Fig. 2 in Taxonomy of the genus Neopanorpa van der Weele, 1909 (Mecoptera, Panorpidae) from the Oriental Region, with the description of two new species

Fig. 2. Neopanorpa luojishana Wang & Hua sp. nov., paratypes (NWAU). A, C–J. Male. A. Habitus, dorsal view. C. Head, frontal view. D. Abdomen, left-lateral view. E–F. Genital bulb, dorsal and ventral views, respectively. G. Right gonostylus, left-lateral view. H. Epandrium and hypandrium, rightlateral view. I–J. Aedeagal complex, ventral and right-lateral views, respectively. – B, K–L. Female. B. Habitus, dorsal view. K. Subgenital plate, ventral view. L. Medigynium, ventral view.

Fig. 5 in Taxonomy of the genus Neopanorpa van der Weele, 1909 (Mecoptera, Panorpidae) from the Oriental Region, with the description of two new species

Fig. 5. Neopanorpa ocellaris (Navás, 1908). A, C–K. Male. A. Habitus, dorsal view. C. Epandrium, dorsal view. D. Head, frontal view. E. T3 and T4, left-lateral view. F. Genital bulb, ventral view. G. Habitus, left-lateral view. H. Left gonostylus, ventral view. I. Epandrium and hypandrium, leftlateral view. J–K. Aedeagal complex, ventral and right-lateral views, respectively. – B, L–N. Female. B. Habitus, dorsal view. L. Subgenital plate, ventral view. M–N. Medigynium, ventral and right-lateral views, respectively.

Fig. 1 in Taxonomy of the genus Neopanorpa van der Weele, 1909 (Mecoptera, Panorpidae) from the Oriental Region, with the description of two new species

Fig. 1. Neopanorpa luojishana Wang & Hua sp. nov., living male. Photo by Ji-Shen Wang from Mt. Luoji, Sichuan, China.