Color Segmentation using LVQ-Learning Vector Quantization

This thesis aims to present a color segmentation approach for traffic sign recognition based on LVQ neural networks. The RGB images were converted into HSV color space, and segmented using LVQ depending on the hue and saturation values of each pixel in the HSV color space. LVQ neural network was used to segment red, blue and yellow colors on the road and traffic signs to detect and recognize them. LVQ was effectively applied to 536 sampled images taken from different countries in different conditions with 89% accuracy and the execution time of each image among 31 images was calculated in between 0.726sec to 0.844sec. The method was tested in different environmental conditions and LVQ showed its capacity to reasonably segment color despite remarkable illumination differences. The results showed high robustness.

Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

Evaluation of Red Colour Segmentation Algorithms in Traffic Signs Detection

Colour segmentation is the most commonly used method in road signs detection. Road sign contains several basic colours such as red, yellow, blue and white which depends on countries.The objective of this thesis is to do an evaluation of the four colour segmentation algorithms. Dynamic Threshold Algorithm, A Modification of de la Escalera’s Algorithm, the Fuzzy Colour Segmentation Algorithm and Shadow and Highlight Invariant Algorithm. The processing time and segmentation success rate as criteria are used to compare the performance of the four algorithms. And red colour is selected as the target colour to complete the comparison. All the testing images are selected from the Traffic Signs Database of Dalarna University [1] randomly according to the category. These road sign images are taken from a digital camera mounted in a moving car in Sweden.Experiments show that the Fuzzy Colour Segmentation Algorithm and Shadow and Highlight Invariant Algorithm are more accurate and stable to detect red colour of road signs. And the method could also be used in other colours analysis research. The yellow colour which is chosen to evaluate the performance of the four algorithms can reference Master Thesis of Yumei Liu.

Brytmånens utformning vid trädfällning - Jämförande studier av böjmotstånd och gångjärnseffekt : Designing felling hinge in tree felling - Comparative studies of bending resistance and hinge effect

Vid trädfällning med motorsåg sparar man en så kallad brytmån som skall fungera som ett gång¬järn när trädet fälls. Om brytmånen går av tidigt finns en risk att trädet faller okontrolle¬rat. De rekommendationer som finns säger att brytmånens bredd skall göras proportionell mot trädets diameter. Genom att teoretiskt och praktiskt undersöka vilka krafter brytmånen utsätts för och vad den håller för har det varit möjligt att dra vissa slutsatser om hur en bra brytmån skall se ut. Ett viktigt resultat är att en bred brytmån (över 30-40 mm) är mycket trög att böja och inte fungerar i det avseendet att den går av redan vid små böjningar. Teoretiska be¬räkningar och praktiska försök visar att en relativt smal brytmån håller för belastningen vid rakt motlut även på stora träd. Som ny rekommendationen föreslås att brytmånens bredd inte bör vara mer än 30 mm. Av försöken kan man också dra slutsatsen att frusen ved är stel och brister tidigt, varför svår¬fällda träd inte bör fällas när veden är fryst.A felling hinge is used when felling trees by help of chain saw. If the hinge breaks early in the fall of the tree there is a great risk that the tree will fall without control. Present recommenda¬tions in Sweden say that the thickness of the felling hinge shall be made in proportion to the stem diameter. By use of theoretical and practical examinations of the forces stressing the felling hinge, and the strength of the wood itself, it has been possible to draw conclusions regarding the correct design of a felling hinge. One important result is that a thick felling hinge (over 30-40 mm) is very hard to bend and does not work well as it looses most of its strength already at a small forward bending angel. Theoretical calculations and practical tests show that a relatively narrow felling hinge will manage very well the forces when felling trees with lean opposite to the felling direction even for large trees. Our new recommendation is that the thickness of the felling hinge in normal Swedish conditions should not exceed 30 mm. Through the studies it can also be seen that frozen, brittle wood breaks at small bending angels. For that reason particularly difficult trees not should be felled when the wood is frozen.

Kraftutveckling för manuella trädfällningsredskap : Force development for manual tree felling tools

The objective with this study has been to build general models of the mechanics in tree felling with chain-saw and to compare felling torque for different tools. The theoretical models are completed and validated with a comparative study. The study includes a great number of felling tools of which some are used with different methods. Felling torque was measured using a naturally like measuring arrangement where a tree is cut at about 3.7 m height and then anchored with a dynamometer to a tree opposite to the felling direction. Notch and felling cut was made as ordinary with exception that the hinge was made extra thin to reduce bending resistance. The tree was consequently not felled during the trials and several combinations of felling tools and individuals could be used on the same tree.The results show big differences between tools, methods and persons. The differences were, however, not general, but could vary depending on conditions (first of all tree diameters). Tools and methods that push or pull on the stem are little affected by the size of the tree, while tools that press on the stump are very much dependent of a large stump-diameter. Hand force asserted on a simple pole is consequently a powerful tool on small trees. For trees of medium size there are several alternative methods with different sizes and brands of felling levers and wedges. Larger and more ungainly tools and methods like tree pusher, winch, etc. develop very high felling torque on all tree sizes. On large trees also the felling wedge and especially the use of several wedges together develop very high felling torque.

Quality management for vital forest tree seedlings : Final report, Project no: P33854-1

The work concerns development of a prototype molecular tests to identify vitality status of conifer seedlings. The work is done by NSure, Holland, Dalarna University and SUAS. In case for spruce, a successful validation experiment has been performed to validate the identified frost tolerance and vitality genes. Multiple indicators were identified that can be used to either reinforce the existing ColdnSure test, but also for development of a vitality test. The identified frost tolerance and vitality genes for pine still need to be validated. NSure together with Dalarna University aim to perform a validation next season. Multiple LN indicators were identified in spruce that can be used to determine the effectiveness of a LN treatment, but they are not yet validated. In spruce and pine hardly any scientific research is performed to study the effect of a LN treatment, particularly not at molecular level. Therefore NSure together with Dalarna Research Station want to apply for a project. Within this project, we would be able to develop the tests further.

Real time video segmentation for recognising paint marks on bad wooden railway sleepers

Wooden railway sleeper inspections in Sweden are currently performed manually by a human operator; such inspections are based on visual analysis. Machine vision based approach has been done to emulate the visual abilities of human operator to enable automation of the process. Through this process bad sleepers are identified, and a spot is marked on it with specific color (blue in the current case) on the rail so that the maintenance operators are able to identify the spot and replace the sleeper. The motive of this thesis is to help the operators to identify those sleepers which are marked by color (spots), using an “Intelligent Vehicle” which is capable of running on the track. Capturing video while running on the track and segmenting the object of interest (spot) through this vehicle; we can automate this work and minimize the human intuitions. The video acquisition process depends on camera position and source light to obtain fine brightness in acquisition, we have tested 4 different types of combinations (camera position and source light) here to record the video and test the validity of proposed method. A sequence of real time rail frames are extracted from these videos and further processing (depending upon the data acquisition process) is done to identify the spots. After identification of spot each frame is divided in to 9 regions to know the particular region where the spot lies to avoid overlapping with noise, and so on. The proposed method will generate the information regarding in which region the spot lies, based on nine regions in each frame. From the generated results we have made some classification regarding data collection techniques, efficiency, time and speed. In this report, extensive experiments using image sequences from particular camera are reported and the experiments were done using intelligent vehicle as well as test vehicle and the results shows that we have achieved 95% success in identifying the spots when we use video as it is, in other method were we can skip some frames in pre-processing to increase the speed of video but the segmentation results we reduced to 85% and the time was very less compared to previous one. This shows the validity of proposed method in identification of spots lying on wooden railway sleepers where we can compromise between time and efficiency to get the desired result.

Color detection and segmentation for road and traffic signs

This paper aims to present three new methods for color detection and segmentation of road signs. The images are taken by a digital camera mounted in a car. The RGB images are converted into IHLS color space, and new methods are applied to extract the colors of the road signs under consideration. The methods are tested on hundreds of outdoor images in different light conditions, and they show high robustness. This project is part of the research taking place in Dalarna University / Sweden in the field of the ITS.

Crown ethers : applications in inorganic synthesis

The ability of macroheterocyclic compounds to complex with ionic species has led to the synthesis and investigation of many multidentate macroheterocyclic species. The most stable complexes are formed between macrocyclic polyetheral ligands (crown ethers) with alkali or alkaline earth metal iona. There is an excellent correlation of the stability of these complexes with the size of the cation and the site of the cavity in the macrocyclic ligand. Additional factors, such as the basicity of the ligand and the solvating ability of the solvent, also play important roles in the stabilization of the complex. The stability of such complexes has been advantageously used to increase anionic reactivity and has been successfully applied to several organic fluorinations, oxidations, and similar reactions. The use of macrocyclic ligands in inorganic syntheses of otherwise difficult to obtain fluoro compounds has not been reported. O-carborane and m-carborane, C2BlOHl2, are icosahedral cage systems derived from Bl2H122- by replacement of BH with the isoelectronic CH group. These stable molecules exhibit electron-deficient bonding which can best be explained by delocalization of electrons. This delocalization gives rise to stability similar to that found in aromatic hydrocarbons. Crown ether activated potassium fluoride has been successfully employed in the conversion of alkyl, acyl and aryl halides to their respective fluorides. Analogously halide substituted carboranes were prepared, but their fluoro-derivatives were not obtained. The application of crown ethers in the synthesis of transition metal complexes is relatively unexplored. The usual synthesis of fluoro-derivative transition metal complexes involves highly reactive and toxic fluorinating agents such as antimony trifluoride, antimony penta fluoride. bromine trifluoride and hydrogen fluoride, An attempted preparation of the hexafluoroosmate (IV) ion via a crown activated, or naked fluoride~was unsuccessful. Potassium hexafluoroosmate (IV), K208F6. was eventually prepared using bromine trifluoride as a fluorinating and oxidizing agent .