Jihed Elouni, Hela Ltifi, Mounir Ben Ayed, M. Masmoudi
{"title":"A visual modeling of knowledge for decision-making","authors":"Jihed Elouni, Hela Ltifi, Mounir Ben Ayed, M. Masmoudi","doi":"10.1109/IVCNZ.2016.7804431","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804431","url":null,"abstract":"Data mining technology plays an important role in uncovering hidden and interesting patterns. Actually the discovering of models and relationships concealed in data extends the possibilities to support decision-making. The objective of this paper is to investigate how decision makers obtain knowledge from the extracted patterns representation. We aim to design an efficient visual tool to articulate the knowledge produced by these patterns. The methodological proposal is applied to existing data mining patterns aiming at assisting physicians in the fight against nosocomial infections in the Intensive Care Units. The usability evaluation of the developed knowledge visualization technique shows that the decision-maker gains better insight in the patterns representation and knowledge acquiring by increasing positive perception and observation from the participants.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127526567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ben Pedersen, D. Bailey, R. Hodgson, Rob Ward Ralph Ball
{"title":"Development of a low cost microfluidic imaging system","authors":"Ben Pedersen, D. Bailey, R. Hodgson, Rob Ward Ralph Ball","doi":"10.1109/IVCNZ.2016.7804464","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804464","url":null,"abstract":"This paper examines some of the issues relating to the design and application of microfluidic channels not aligned perpendicularly to the optical axis of the image acquisition system. This technique finds potential application to the automation of lab-based cytometry tasks such as counting and classifying pollen or nematode eggs. Flow through such tilted microchannels will cause objects to move through the focal plane of the image acquisition system, allowing Z-stack images to be collected from which in-focus images of complete objects can be assembled. The design of such systems is discussed and equations are presented that relate to the interaction of the key design factors. Candidate materials are compared for the purpose of producing low cost microchannels for use in tilted channel devices and suggestions made. This paper represents work in progress on a continuing project.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124701513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Early diagnosis of Alzheimer's disease: A multi-class deep learning framework with modified k-sparse autoencoder classification","authors":"Pushkar Bhatkoti, M. Paul","doi":"10.1109/IVCNZ.2016.7804459","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804459","url":null,"abstract":"Successful, timely diagnosis of neuropsychiatry diseases is key to management. Research efforts in the area of diagnosis of Alzheimer's disease have used various aspects of computer-aided multi-class diagnosis approaches with varied degrees of success. However, there is still need for more efficient and reliable approaches to successful diagnosis of the disease. This research used deep learning framework with modified k-sparse autoencoder (oKSA) classification to locate neutrally degenerated areas of the brain magnetic resonance imaging (MRI), low amyloid beta 1-42 imaging in cerebrospinal fluid (CSF) and positron emission tomography (PET) imaging of amyloid; each with a sample of 150 images. Results show a correlation between computational demarcation of infected regions and the images. Degeneration in the studied areas was evidenced by high phosphorylated t-/p-tau levels in CSF, regional fluorodeoxyglucose PET, and the presence of atrophy patterns. The use of σKSA algorithm in boosting classification helped to improve the classifier performance. The KSA method with deep learning framework is used for the first time to produce accurate results in diagnosis of Alzheimer's disease.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130396162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Extreme imaging: Macromolecular imaging using x-ray free-electron lasers","authors":"R. Millane, David H. Wojtas, R. D. Arnal","doi":"10.1109/IVCNZ.2016.7804466","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804466","url":null,"abstract":"X-ray free-electron lasers are new x-ray sources that are revolutionising high resolution molecular imaging. These sources produce extremely bright and extremely brief x-ray pulses that can overcome limitations of crystal growth and radiation damage in traditional protein x-ray crystallography. They introduce a new paradigm in diffraction imaging in which the specimen is destroyed, but not before the diffraction data are collected, and that requires radically new forms of specimen delivery and data processing. An overview of biomolecular imaging using x-ray free-electron lasers is provided, as well as future prospects.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"117 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120862622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Practical application of the geometric wavefront sensor for adaptive optics","authors":"S. Pal, A. Lambert, S. Weddell","doi":"10.1109/IVCNZ.2016.7804427","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804427","url":null,"abstract":"Wavefront sensors measure specific properties, either in the optical pupil plane or indirectly at the image plane; the former uses incident light in the pupil of an optical system, whereas the later employs one or more focal plane sensors to recover the wave front. Phase perturbations, in the form of low-order Zernike coefficients, e.g., defocus (Z5) in this case, are introduced using a bimorph deformable mirror. We investigate the practical application of the geometric wave front sensor (WFS), using a versatile optical test-bench to emulate the effects of wave front propagation in an open-loop configuration. In this paper, the estimation of residual wave front error, for a user-generated aberration, is further verified using simulation results.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126478402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Extending the depth of field in microscopy: A review","authors":"Anoop Suraj Ambikumar, D. Bailey, G. S. Gupta","doi":"10.1109/IVCNZ.2016.7804448","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804448","url":null,"abstract":"This paper investigates multi-focus image fusion methods in the context of microscope. Limited depth of field is one of the major limitations in microscopy. Objects which are thicker than the depth of field cannot be captured completely within one sharp image. The solution is to capture multiple images at different focus and fuse them to derive a single sharp image. Spatial domain and transform domain (including frequency domain, multiscale analysis and wavelet transform) are considered. Most applications are limited in their performance by real-time constraints such as speed, resource utilization etc. Dedicated hardware based on FPGAs is one solution to overcome this limitation. A focus of this review is given towards exploring the hardware implementation and related issues of multi-focus image fusion for microscopic applications. The review concludes with a number of outstanding challenges, and potential directions for further research.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114392706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Stromer, G. Anton, V. Christlein, A. Maier, P. Kugler
{"title":"3-D reconstruction of historical documents using an X-Ray C-Arm CT system","authors":"D. Stromer, G. Anton, V. Christlein, A. Maier, P. Kugler","doi":"10.1109/IVCNZ.2016.7804468","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804468","url":null,"abstract":"There exist historical documents that can not be inspected without damaging them. We present a non-invasive method for the reconstruction of historical documents which have been written with iron gall ink. Iron gall ink has been used since the 5th century and is still in use as an indelible ink for writings and drawings. The fact, that this kind of ink is based on metallic particles leads to the assumption that modern X-Ray scanners could image the writings such that it can be differentiated from the paper mainly consisting of cellulose. Our work shows a method that is capable of imaging writings written with iron gall ink by using a modern X-Ray imaging system that is commonly used for medical applications. Even though the imaging system is not optimized for the given task, the writing can be identified. Furthermore, we present a method that is able to reconstruct the volume even if the phantom is not centered properly or misaligned. Applying this method makes it possible to image books, writings or drawings based on all metal-containing inks without page-turning or unrolling the paper.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127948359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fahimeh Alaei, Alireza Alaei, M. Blumenstein, U. Pal
{"title":"Document image retrieval based on texture features and similarity fusion","authors":"Fahimeh Alaei, Alireza Alaei, M. Blumenstein, U. Pal","doi":"10.1109/IVCNZ.2016.7804437","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804437","url":null,"abstract":"In this paper we investigate the usefulness of two different texture features along with classification fusion for document image retrieval. A local binary texture method, as a statistical approach, and a wavelet analysis technique, as a transform-based approach, are used for feature extraction and two feature vectors are obtained for every document image. The similarity distances between each of the two feature vectors extracted for a given query and the feature vectors extracted from the document images in the training step are computed separately. In order to use the properties of both features, a classifier fusion technique is then employed using a weighted average fusion of distance measures obtained in relation to each feature vector. The document images are finally ranked based on the greatest visual similarity to the query obtained from the fusion similarity measures. The Media Team Document Database, which provides a great variety of page layouts and contents, is considered for evaluating the proposed method. The results obtained from the experiments demonstrate a correct document retrieval of 65.4% and 91.8% in the Top-1 and Top-10 ranked document list, respectively.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122160710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"How to predict lightness variations from one illuminant to another?","authors":"S. L. Moan","doi":"10.1109/IVCNZ.2016.7804447","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804447","url":null,"abstract":"The notion of subjective image quality (SIQ) is particularly difficult to define as it depends on a large variety of physical attributes and psycho-physical factors. One important attribute which SIQ depends on is the illumination under which visual stimuli are observed. Recent studies have shown that achromatic fidelity (i.e. perceived resemblance in lightness) is significantly less dependent on illumination than other perceptual attributes such as chroma and hue. These findings were used to develop the 5-dimensional extended colour space LabAB, which uses a single lightness channel to represent 31-dimensional multispectral (reflectance) data for efficient, perception-driven processing in spectral reproduction workflows. This channel, which is derived from the perceptually uniform LAB2000HL colour space with CIE D50 white point, is meant to approximate the perceived lightness under most light sources. However, little is known as to how accurate this approximation actually is. For instance, if a spectral cross-media reproduction application requires a high quality of reproduction under both daylight and LED light, will LabAB and its daylight-based lightness channel be a good enough representation to capture and convey all attributes of SIQ throughout the reproduction workflow? A metric that would allow to evaluate the reliability of using a single lightness dimension to represent spectral data for a given application is desirable. Here, I investigate how several spectral and colour difference measures perform at estimating this reliability.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121091202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Zollmann, Christian Poglitsch, Jonathan Ventura
{"title":"VISGIS: Dynamic situated visualization for geographic information systems","authors":"S. Zollmann, Christian Poglitsch, Jonathan Ventura","doi":"10.1109/IVCNZ.2016.7804440","DOIUrl":"https://doi.org/10.1109/IVCNZ.2016.7804440","url":null,"abstract":"Situated Visualization techniques are visualization techniques that provide a presentation of information within its spatial context. Situated Visualization techniques have several advantages compared to traditional visualization techniques with the biggest advantage being providing the spatial relationship between data and the actual environment. However, Situated Visualization techniques are also subject to several challenges. In particular, Situated Visualization of data from geographic information systems (GIS) is exposed to a set of problems, such as limited visibility, legibility, information clutter and the limited understanding of spatial relationships. In this paper, we address the challenges of visibility, information clutter and understanding of spatial relationships with a set of dynamic Situated Visualization techniques that address the special needs of Situated Visualization of GIS data in particular for “street-view”-like perspectives as used for many navigation applications. The proposed techniques include dynamic annotation placement, dynamic label alignment and occlusion culling. We applied those techniques for two types of Situated Visualizations: Augmented Reality visualization and Indirect Augmented Reality using 360 Degree footage.","PeriodicalId":396385,"journal":{"name":"2016 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123760781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}