идентификация оружия

Classifi cation of fi ring pin marks images by weapon specimens using a fully-connected neural network

Introduction. The aim of the work is to increase the effi ciency of identifi cation of fi rearms by images of fi ring pin marks in the automatic mode. The relevance of the task is determined by the low effi ciency of the known methods of automatic identifi cation of fi rearm by the fi ring pin marks with individual topological types of individualizing features. This aff ects the investigation of crimes related to the use of fi rearms. Formation of clone images. A training sample was formed; it included 140 original images of fi ring pin marks from 50 classes, on the basis of which about 1000 clone images were made with slightly modifi ed individualizing features. In this case a specifi c specimen of a fi rearm is meant as a class. Neural network training. A fully connected neural network with the following architecture was used as a classifi er: an input layer of neurons; two hidden layers; an output layer. The input layer included 2500 neurons, the fi rst hidden layer was made up of 625 neurons, the second hidden layer contained 156 neurons; the output layer consisted of 50 neurons (in accordance with the number of the classes). Evaluation of the calculation results. The prediction accuracy of the trained neural network was estimated according to the Accuracy metric, which is the ratio of the number of correct predictions to the total number of predictions. The prediction accuracy for the maximum signal on one output neuron was 81%, and when the maximum signals on three output neurons were taken into account, the accuracy was about 91%. Conclusions. The research has shown the possibility of classifi cation of the images of fi ring pin marks by weapons using a fully connected neural network, as well as the eff ectiveness of using artifi cially generated clone images of fi ring pin marks for training a fully connected neural network in cases with a small number of initial objects.

A Probabilistic Assessment of the Complexes of Combined Traces in Secondary Tracks on Fired Bullets

Introduction. The paper analyzes the effectiveness of the application of the method of successively matching traces (CMS method) and the probabilistic method for substantiating the forensic identity of the overlapping secondary traces on fired bullets. Theoretical analysis. The theoretical foundations of the CMS method and the probabilistic method are considered. It is shown that the second method is formed on the basis of two mutually complementary probabilistic models. Experimental studies of the effectiveness of assessing the uniqueness of the complexes of combined tracks. The studies were conducted for secondary traces with high and low track density (for tracks on bullets fired from PM and AK-74, respectively). Potential trace identity criteria were defined for traces with low track density according to the CMS method. The authors determined the probabilistic criteria for the identity of the compared traces with high and low track density. It is shown that for traces with a low track density, the criterion of potential identity is the probability of random alignment of tracks no more than 5*10-3, and for traces with a high density of tracks the probability is no more than 10-6. Results. The probabilistic method allows you to obtain a quantitative assessment of the uniqueness of coincident features and correctly substantiate a categorical positive conclusion when identifying firearms by traces on fired bullets.

The Method of the Estimation of Uniqueness of Route Complexes in Secondary Traces

Introduction. The existing criteria for the pairing of traces on shot bullets can not be considered satisfactory. They turn out to be too strict, or do not take into account the identifiable information about the structure of the coincident traces. Therefore, today expert makes categorical conclusion about the identity of the compared traces mainly on bases on his own experience without assessing the probability of a random realization of this event. In this paper, a technique for estimation of the uniqueness of the route complexes in compared traces is considered. In general, the solution of this problem allows us to objectify the expert conclusions. Theoretical analysis. In work the model describing the structure of the routes displayed on the surface of a shot bullet is proposed. On the basis of this model, a method for assessment of the probability of a random coincidence of the routes (the uniqueness of the complexes of coinciding routes) is proposed. Priority list of the similarity of traces is proposed to be formed on the basis of an assessment of the uniqueness of complexes of coincident routes. Empirical analysis. The results of applying the proposed methodology using the proposed pairing criterion are presented. We used two models of weapons: AKM and Makarov pistol. Results. Comparison of test paired and unpaired traces with an assessment of the uniqueness of complexes of coincident routs showed the effectiveness of the proposed methodology and the objectivity of assessing the degree of similarity of the traces.

Influence of Inhomogeneities of the Surface of Caps on Variability of Static Firing Pin Traces

Introduction. One of the reasons for the variability of the firing pin traces is the gross inhomogeneity present on the surface of the capsules. The main types of not uniformity characteristic of a cap surface, and also their display in static traces are quickly investigated in this work. Experimental part. The surfaces of capsules of various cartridges of domestic and foreign production, as well as capsules “Zhevello” for hunting cartridges, were examined. The main types of inhomogeneities of the capsule surface are analyzed and classified. During the research it was shown that some roughness of the capsule surface does not smooth out when the striker firing pins and can introduce distortions into the static firing pin traces. Conclusions. The carried out researches have shown that the mismatched strongly pronounced features in pair traces can be explained by the presence of similar inhomogeneities on the surface of the capsule outside of the firing pin trace. This fact should be taken into account when comparing static traces of strikers. The work is of interest to firearm examiner specializing in the identification of weapons.

Method of the Binarization of Images of Traces on the Shot Bullets for the Automatic Assessment of Their Suitability to Identification of the Fierarms

Introduction. Nowadays, automatic identification of weapons on electronic databases involves the analysis thousands of images of similar tracks, including images which are not suitable for identification. It is necessary to exclude from the analysis traces not suitable for identification for reduction of volume of calculations and increase of their efficiency. The aim of this work is the analysis of methods for assessing the suitability of traces to the identification and develop image binarization techniquie, which ensures minimal distortion of the width tracks on traces on the shot bullets. Theoretical analysis. There are two methods for evaluating of the suitability of dynamic traces to identify the weapon. The first is to count the number of lines, the width of the tracks and the spaces between them. The second is to find the autocorrelation function (ACF). The ACF form is close to a delta function form for a trace suitable for identification. The second method is more promising for the analysis of traces on the shot bullets. Experimental part. The authors proposed an image binarizatiom technique based on the construction of the image brightness profile. Application of this technique to images of dynamic traces, which are oriented vertically, allows adequately display the main tracks on binary images. Conclusion. The proposed method allows to get a binary image of traces on the shot bullets suitable for automatic analysis of their suitability for identifying and further comparing traces.

The Concept of Mathematical Model of the Assessment of Uniqueness of Sets of Coinciding Routes in Secondary Traces on the Shot Bullets

Introduction. The model of an assessment of probability of casual combination of sets of routes in secondary traces is considered in article. Development of quantitative criteria of justification of a categorical positive conclusion about criminalistic identity of the compared traces, and also algorithm of formation in the automatic mode of the priority list is the purpose of the conducted research. Theoretical part. Twodimensional images of traces of rifling fields used for the simulation. The formulas for estimating the probability of an accidental match of trails were obtained. Experimental part. Calculations performed on the developed formulas, the dependence of the probability of an event compared to the number of trails should be shown. Conclusion. The theoretical possibility of estimating the probability of a random alignment sets of trails (the degree of matching features unique complexes) and its use in practice is shown in this paper.

The Comparison of Digital Images of Firing Pin with a Dominant Features in the Form of Circles and Arcs

Introduction. Development of the algorithms for the automatic comparison of the digital images of firing pin is an important task of the forensic examination. This task is aimed at improving the efficiency of crime investigation involving the use of firearms. In this paper images of firing pin with the features in the form of circles and arcs with single center are investigated. The method based on modified Euclidean distance between circles of the similar firing pin was proposed to assess the degree of similarity of the traces. Preliminary processing. To eliminate the adverse effect of noise and various image artifacts were pretreated. Markers were placed to accurately determine the features in the form of circles. Method of searching paired tracks. Criteria based on modified Euclidean distance were developed for the formation of the priority list. Numerical experiment. In the numerical experiment database of 60 objects was used. Paired trace from firing pin array was included in top four of the prior list in 90 percent cases. Conclusions. The proposed algorithm allows to sort effectively and quickly the array of test objects by the degree of similarity of signs in the form of arcs and circles with relevant features of the test track.

Problems of Ensuring Compliance of Technical Characteristics of Civil and Office Firearms to Criminalistic Requirements of the Ministry of Internal Affairs of Russia

Introduction. Problematic issues of providing the criminalistic requirements of the Ministry of Internal Affairs of Russia imposed to firearms are considered in work. A sometimes weapons does not provide formation on the shot bullets and cartridge cases of the traces suitable for identification. Absence of any standards or specifications on a roughness of a relief of surfaces of the details forming traces is to it the reason. In addition, arms manufacturers poorly represent modern methods and technical means of identification of the weapon. Experimental part. In work the reasons of formation of traces on the shot bullets and shot cartridge cases not suitable for identification of the weapon are analyzed. Cases where the identification of the weapons on the striker traces is impossible due to the design of shells hunting cartridges are shown in the article. The negative influence of the production of primers traces at identifying of weapons on firing pin traces is quickly studied. Conclusion. Forensic requirements for identification of the weapon can be most effectively provided at close scientific and technical cooperation of the arms manufacturers and scientists specializing in area of judicial identification of the weapon.


Введение. Одной из важнейших задач судебно-баллистической экспертизы является идентификация оружия по следам бойка. Данная задача обычно связана с поиском совпадающих (парных) следов по большим базам данных. Для этого широко используются баллистические идентификационные системы, такие как ПОИСК, ТАИС, Арсенал и другие, в которых исполь- зуются автоматические алгоритмы поиска парных следов, основанные на подсчете функции взаимной кросс-корреляции. В данной работе предложен иной подход, разработанный для изображений следов бойков, содержащих признаки в виде крупных областей неопределенной формы. К ним применялись методы кластерного анализа для формирования приоритетного списка. Теоретическая часть. В теоретической части дается алгоритм выделения и сравнения дескрипторов – характеристик, описывающих изображения следа бойка. После чего предложен способ формирования приоритетного списка, анализируя который, эксперт сможет сделать вывод о парности следов. Экспериментальная часть. Разработанный алгоритм был применен к базе данных, состоящей из более чем 100 изображений следов бойков 24 экземпляров оружия. Заключение. Разработанный алгоритм позволяет формировать приоритетный список из 20 изображений, в который входят парные следы (если такие имеются в электронной базе данных) с вероятностью 100%. Таким образом, предложенная методика позволяет существенно сократить время поиска следов. Данный алгоритм осуществляет предварительную фильтрацию и позволяет выделить список следов, к которым имеет смысл применять более сложные критерии, такие как сравнение контуров, особых точек изображений и т.п.


Введение. Актуальность работы обусловлена широким внедрением автоматизированных баллистических идентификационных систем (АБИС) в баллистические лаборатории экспертных учреждений России. Баллистические системы позволяют автоматизировать проведение проверок по гильзотекам, содержащим тысячи однотипных объектов. Однако в отдельных случаях системы допускают «промахи», т.е. не могут найти в массиве электронной гильзотеки «парный» след (след, оставленный тем же экземпляром оружия, что и исследуемый). Кроме этого, иногда «парный» след из тестового массива ставится в конце приоритетного списка, что осложняет работу эксперта. Это обусловлено, в первую очередь, большим морфологическим разнообразием и высокой вариативностью индивидуальных признаков оружия, отобразившихся в следах бойков, а также неравномерным освещением следов из-за их сложной формы. Теоретический анализ. Исследования показали, что неравномерность яркости цифровых изображений следов бойков может быть сглажена путем применения метода гомоморфной обработки изображений. Анализ морфологии индивидуальных признаков оружия, отобразившихся в следах бойков более 30 моделей оружия, позволил выделить 6 основных морфологических типов признаков. Экспериментальное исследование. Разработаны эффективные алгоритмы выделения и бинаризации признаков в виде крупных пятен неопределенной формы на основе применения фильтра Винера и метода Ниблэка. Для выделения признаков в виде окружностей предложен метод, основанный на применении фильтра Канни. Данные алгоритмы могут найти применение при разработке программного обеспечения баллистических систем, а также при обработке цифровых изображений следов бойков при проведении экс пертных исследований. Выводы. Метод гомоморфной обработки цифровых изображений может быть рекомендован для предварительной обработки исходных изображений. Впервые предложена классификация морфологических типов индивидуальных признаков. Разработаны алгоритмы бинаризации изображений с индивидуальными признаками в виде областей неопределенной формы и в виде окружностей