Weed Recognition Using Image-Processing Technique Based on Leaf Parameters

Weeds normally grow in patches and spatially distributed in field. Patch spraying to control weeds has advantages of chemical saving, reduced cost and environmental pollution. Advent of electro-optical sensing capabilities has paved the way of using machine vision technologies for patch spraying. Machine vision system has to acquire and process digital images to make control decisions. Proper identification and classification of objects present in image holds the key to make control decisions and use of any spraying operation performed. Recognition of objects in digital image may be affected by background, intensity, image resolution, orientation of the object and geometrical characteristics. A set of 16, including 11 shape and 5 texture-based parameters coupled with predictive discriminating analysis has been used to identify the weed leaves. Geometrical features were indexed successfully to eliminate the effect of object orientation. Linear discriminating analysis was found to be more effective in correct classification of weed leaves. The classification accuracy of 69% to 80% was observed. These features can be utilized for development of image based variable rate sprayer.

Image-processing techniques in precisely measuring positions of Saturn and its satellites

After overcoming the deficiencies of previous image-processing techniques, a novel technique based on the edge-detection of Saturnian ring is developed to precisely measure Saturn’s position. Furthermore, the scattering light (i.e. halo light) of Saturn and its ring is removed effectively based on its center symmetry. Therefore, we have much more opportunities to accurately measure the positions of Mimas and Enceladus—two satellites very close to the Saturn. Experimental tests with 127 frames of CCD images obtained on the 1-meter telescope at the Yunnan Obeservatory over three nights show that the geometric center of the Saturnian ring and its 4 satellites (Tethys, Dione, Rhea and Titan) have the same positional precision, and the standard error for a single observation is less than ±0.05 arcsec. It is believed that these new techniques would have important impetus to the positional measurement of both Saturn by using a CCD meridian instrument and its faint satellites by using a long focal length telescope.

Application of multi-planar reconstruction technique in endovascular repair of aortic dissection

BACKGROUND Endovascular repair of aortic dissection is an effective method commonly used in the treatment of Stanford type B aortic dissection.Stent placement during the operation was one-time and could not be repeatedly adjusted during the operation.Therefore,it is of great significance for cardiovascular physicians to fully understand the branch status,position,angle,and other information regarding aortic arch dissection before surgery.AIM To provide more references for clinical cardiovascular physicians to develop treatment plans.METHODS Data from 153 patients who underwent endovascular repair of aortic dissection at our hospital between January 2021 and December 2022 were retrospectively collected.All patients underwent multi-slice spiral computed tomography angiography.Based on distinct post-image processing techniques,the patients were categorized into three groups:Multiplanar reconstruction(MPR)(n=55),volume reconstruction(VR)(n=46),and maximum intensity projection(MIP)(n=52).The detection rate of aortic rupture,accuracy of the DeBakey classification,rotation,and tilt angles of the C-arm during the procedure,dispersion after stent release,and the incidence of late complications were recorded and compared.RESULTS The detection rates of interlayer rupture in the MPR and VR groups were significantly higher than that in the MIP group(P<0.05).The detection rates of De-Bakey subtypesⅠ,Ⅱ,andⅢin the MPR group were higher than those in the MIP group,and the detection rate of typeⅢin the MPR group was significantly higher than that in the VR group(P<0.05).There was no statistically significant difference in the detection rates of typesⅠandⅡcompared to the VR group(P>0.05).The scatter rate of markers and the incidence of complications in the MPR group were significantly lower than those in the VR and MIP groups(P<0.05).CONCLUSION The application of MPR in the endovascular repair of aortic dissection has improved the detection rate of dissection rupture,the accuracy of anatomical classification,and safety.

Robust Vehicle Detection Based on Improved You Look Only Once

Vehicle detection is still challenging for intelligent transportation systems(ITS)to achieve satisfactory performance.The existing methods based on one stage and two-stage have intrinsic weakness in obtaining high vehicle detection performance.Due to advancements in detection technology,deep learning-based methods for vehicle detection have become more popular because of their higher detection accuracy and speed than the existing algorithms.This paper presents a robust vehicle detection technique based on Improved You Look Only Once(RVD-YOLOv5)to enhance vehicle detection accuracy.The proposed method works in three phases;in the first phase,the K-means algorithm performs data clustering on datasets to generate the classes of the objects.Subsequently,in the second phase,the YOLOv5 is applied to create the bounding box,and the Non-Maximum Suppression(NMS)technique is used to eliminate the overlapping of the bounding boxes of the vehicle.Then,the loss function CIoU is employed to obtain the accurate regression bounding box of the vehicle in the third phase.The simulation results show that the proposed method achieves better results when compared with other state-of-art techniques,namely LightweightDilated Convolutional Neural Network(LD-CNN),Single Shot Detector(SSD),YOLOv3 and YOLOv4 on the performance metric like precision,recall,mAP and F1-Score.The simulation and analysis are carried out on PASCAL VOC 2007,2012 and MS COCO 2017 datasets to obtain better performance for vehicle detection.Finally,the RVD-YOLOv5 obtains the results with an mAP of 98.6%and Precision,Recall,and F1-Score are 98%,96.2%and 97.09%,respectively.

A Novel Approach for Face Recognition Based on a Multiple Faces Database

This paper presents an algorithm and then MATLAB program that can construct and process an image depending on a given database and face recognition technique, which helps in the operations of investigation issues for policemen and in any similar operations, the image gets constructed and implemented as the database is developed. It is found that such image processing operation helps in operations needs quick investigation transactions of some issues like policemen works and operations. The method depends on the given database about the face of the person, the face recognition depends on drawing a face of the given data and then comparing the resulted face with the stored data and find the most closes one and choose it to be its goal. This operation needs a time, it is not real-time operation but the time needed is too short. This method develop a method to make the operation of searching about some unknown person or face faster which helps more all sectors interested in searching about some unknowns in their transactions.

A review of applications of visual inspection technology based on image processing in the railway industry

In order to ensure the safety of railway transportation,it is necessary to regularly check for faults and defects in the railway system.Visual inspection technology is conducive to improving the low efficiency,poor economy and inaccurate detection results of traditional detection methods.This paper introduces the research and contribution of various scholars in the field of visual inspection,summarizes the application and development of visual inspection technology in the railway industry,and finally forecasts the future research direction of visual inspection technology.

Real-time recognition of sows in video: A supervised approach

This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup’s image processing module where there is lack of statistical information regarding the background.A set of 7 farrowing sessions of sows,during day and night,have been captured(approximately 7 days/sow),which is used for this study.The frames of these recordings have been grabbed with a time shift of 20 s.A collection of 215 frames of 7 different sows with the same lighting condition have been marked and used as the training set.Based on small neighborhoods around a point,a number of image local features are defined,and their separability and performance metrics are compared.For the classification task,a feed-forward neural network(NN)is studied and a realistic configuration in terms of an acceptable level of accuracy and computation time is chosen.The results show that the dense neighborhood feature(d.3×3)is the smallest local set of features with an acceptable level of separability,while it has no negative effect on the complexity of NN.The results also confirm that a significant amount of the desired pattern is accurately detected,even in situations where a portion of the body of a sow is covered by the crate’s elements.The performance of the proposed feature set coupled with our chosen configuration reached the rate of 8.5 fps.The true positive rate(TPR)of the classifier is 84.6%,while the false negative rate(FNR)is only about 3%.A comparison between linear logistic regression and NN shows the highly non-linear nature of our proposed set of features.

Experimental-computational study of fibrous particle transport and deposition in a bifurcating lung model

Experiments carried out using a lung model with a single horizontal bifurcation under different steady inhalation conditions explored the orientation of depositing carbon fibers, and particle deposition frac- tions. The orientations of deposited fibers were obtained from micrographs. Specifically, the effects of the sedimentation parameter （γ）, fiber length, and flow rate on orientations were analyzed. Our results indicate that gravitational effect on deposition cannot be neglected for 0.0228 〈 γ 〈 0.247. The absolute orientation angle of depositing fibers decreased linearly with increasing y for values 0.0228 〈 γ 〈 0.15. Correspondence between Stokes numbers and y suggests these characteristics can be used to estimate fiber deposition in the lower airways. Computer simulations with sphere-equivalent diameter models for the fibers explored deposition efficiency vs. Stokes number. Using the volume-equivalent diameter model, our experimental data for the horizontal bifurcation were replicated. Results for particle deposition using a lung model with a vertical bifurcation indicate that body position also affects deposition.