Based on the analysis of the subjectivity of wetland boundary criteria and their causes at present, this paper suggested that, under the condition that the mechanism of wetland formation process has not been understoo...Based on the analysis of the subjectivity of wetland boundary criteria and their causes at present, this paper suggested that, under the condition that the mechanism of wetland formation process has not been understood, "black box" method of System Theory can be used to delineate wetland boundaries scientifically. After analyzing the difference of system construction among aquatic habitats, wetlands and uplands, the lower limit of rooted plants was chosen as the lower boundary criterion of wetlands. Because soil diagnostic horizon is the result of the long-term interaction among all environments, and it is less responsive than vegetation to short-term change, soil diagnostic horizon was chosen as the indicator to delineate wetland upper boundary, which lies at the thinning-out point of soil diagnostic horizon. Case study indicated that it was feasible using the lower limit of rooted plants and the thinning-out point of soil diagnostic horizon as criteria to delineate the lower and upper boundaries of wetland. In the study area, the thinning-out line of albic horizon was coincident with the 55.74m contour line, the maximum horizon error was less than 1m, and the maximum vertical error less than 0.04m. The problem on wetland definition always arises on the boundaries. Having delineated wetland boundaries, wetlands can be defined as follows: wetlands are the transitional zones between uplands and deepwater habitats, they are a kind of azonal complex that are inundated or saturated by surface or ground water, with the lower boundary lying at the lower limit of rooted plants, and the upper boundary at the thinning-out line of upland soil diagnostic horizon.展开更多
The pupil recognition method is helpful in many real-time systems,including ophthalmology testing devices,wheelchair assistance,and so on.The pupil detection system is a very difficult process in a wide range of datas...The pupil recognition method is helpful in many real-time systems,including ophthalmology testing devices,wheelchair assistance,and so on.The pupil detection system is a very difficult process in a wide range of datasets due to problems caused by varying pupil size,occlusion of eyelids,and eyelashes.Deep Convolutional Neural Networks(DCNN)are being used in pupil recognition systems and have shown promising results in terms of accuracy.To improve accuracy and cope with larger datasets,this research work proposes BOC(BAT Optimized CNN)-IrisNet,which consists of optimizing input weights and hidden layers of DCNN using the evolutionary BAT algorithm to efficiently find the human eye pupil region.The proposed method is based on very deep architecture and many tricks from recently developed popular CNNs.Experiment results show that the BOC-IrisNet proposal can efficiently model iris microstructures and provides a stable discriminating iris representation that is lightweight,easy to implement,and of cutting-edge accuracy.Finally,the region-based black box method for determining pupil center coordinates was introduced.The proposed architecture was tested using various IRIS databases,including the CASIA(Chinese academy of the scientific research institute of automation)Iris V4 dataset,which has 99.5%sensitivity and 99.75%accuracy,and the IIT(Indian Institute of Technology)Delhi dataset,which has 99.35%specificity and MMU(Multimedia University)99.45%accuracy,which is higher than the existing architectures.展开更多
基金Under the auspices of the Knowledge Innovation Program of Chinese Academy of Sciences(No.KZCX3-SW-NA-01)
文摘Based on the analysis of the subjectivity of wetland boundary criteria and their causes at present, this paper suggested that, under the condition that the mechanism of wetland formation process has not been understood, "black box" method of System Theory can be used to delineate wetland boundaries scientifically. After analyzing the difference of system construction among aquatic habitats, wetlands and uplands, the lower limit of rooted plants was chosen as the lower boundary criterion of wetlands. Because soil diagnostic horizon is the result of the long-term interaction among all environments, and it is less responsive than vegetation to short-term change, soil diagnostic horizon was chosen as the indicator to delineate wetland upper boundary, which lies at the thinning-out point of soil diagnostic horizon. Case study indicated that it was feasible using the lower limit of rooted plants and the thinning-out point of soil diagnostic horizon as criteria to delineate the lower and upper boundaries of wetland. In the study area, the thinning-out line of albic horizon was coincident with the 55.74m contour line, the maximum horizon error was less than 1m, and the maximum vertical error less than 0.04m. The problem on wetland definition always arises on the boundaries. Having delineated wetland boundaries, wetlands can be defined as follows: wetlands are the transitional zones between uplands and deepwater habitats, they are a kind of azonal complex that are inundated or saturated by surface or ground water, with the lower boundary lying at the lower limit of rooted plants, and the upper boundary at the thinning-out line of upland soil diagnostic horizon.
文摘The pupil recognition method is helpful in many real-time systems,including ophthalmology testing devices,wheelchair assistance,and so on.The pupil detection system is a very difficult process in a wide range of datasets due to problems caused by varying pupil size,occlusion of eyelids,and eyelashes.Deep Convolutional Neural Networks(DCNN)are being used in pupil recognition systems and have shown promising results in terms of accuracy.To improve accuracy and cope with larger datasets,this research work proposes BOC(BAT Optimized CNN)-IrisNet,which consists of optimizing input weights and hidden layers of DCNN using the evolutionary BAT algorithm to efficiently find the human eye pupil region.The proposed method is based on very deep architecture and many tricks from recently developed popular CNNs.Experiment results show that the BOC-IrisNet proposal can efficiently model iris microstructures and provides a stable discriminating iris representation that is lightweight,easy to implement,and of cutting-edge accuracy.Finally,the region-based black box method for determining pupil center coordinates was introduced.The proposed architecture was tested using various IRIS databases,including the CASIA(Chinese academy of the scientific research institute of automation)Iris V4 dataset,which has 99.5%sensitivity and 99.75%accuracy,and the IIT(Indian Institute of Technology)Delhi dataset,which has 99.35%specificity and MMU(Multimedia University)99.45%accuracy,which is higher than the existing architectures.
