Our Wayne Gretzky autograph verifications
Four easy steps to get your Wayne Gretzky memorabilia verified or appraised:
Is this jersey actually signed by Wayne Gretzky?
Signed drawings
Description of jersey to authenticate
The item in focus is a framed hockey jersey displaying the iconic number ”99,” immediately recognizable as belonging to Wayne Gretzky. The signature is placed meticulously at the top of the second digit ”9” on the back of the jersey, a location that draws the eye to both the autograph and the number emblematic of Gretzky’s identity. The signature itself is executed with a bold, confident stroke, indicative of Gretzky’s style. It features a legible ”W” and ”G,” which flow into a series of curves that suggest the rest of his name, all penned in a black marker that stands out against the orange backdrop of the jersey number.
The jersey is professionally mounted within a shadow box frame, which includes a descriptive plaque, adding to the item’s presentation and value. As shown in Figure 1, the plaque is an integral part of the jersey’s display. Such memorabilia is not only a tribute to one of hockey’s greatest players but also a collectible that commands attention and respect in the sports memorabilia market. The careful placement and clear visibility of the signature enhance the jersey’s appeal as a piece of sports history. As time progresses, the combination of Gretzky’s celebrated career and the rarity of signed items like this one may contribute to an increase in its value among collectors and enthusiasts.
GETTING READY
Processing the signatures
We converted the photos of signatures into squared B/W images, to use as input for our neural network, which works with sub-images of 256x256 pixels. 70% of the authentic signatures were separated for training, 10% for validation, and the remaining 20% were reserved for testing. We placed in a different folder the unknown signatures the customer provided us with.
Analyzing the signature
We employed our AI-based mathematical model, specially trained on digitized images of authentic signatures of Wayne Gretzky extracted from jerseys and other merchandise items. These Admitted Signatures served as our foundation, supplemented with a dataset of Skilled Forgeries. To achieve peak classification accuracy, we optimized the images for robust feature map extraction.
Training our neural network
Our neural networks are trained on the images of our verified authentic signatures
The number of available authentic signatures is finite, so we perform data augmentation: This means randomly translating and rotating the shape of the signature in the squared images. This improves the accuracy of the classification. Additionally, it is also zoomed in and out a bit.
- We trained our model using the authentic samples and skilled forgeries. For this task, we used two networks, an encoder and a decoder, which is able to reconstruct the signatures. After obtaining training convergence, we saved the trained model.
OUR VERDICT
Using our trained model to test the signatures
During testing we compute a probability of the signatures to be authentic.
- Technically, this is the similarity of the feature maps obtained with each test signature compared to the ones extracted during training with the authentic ones.
For testing, we used 20 fake and 20 authentic signatures, which were not seen by the model during training. As a result, of these, 95% of the signatures have been correctly classified.
Need help to authenticate or value an item?
We offer a personalized service to our customers. Only four easy steps to get an item verified or valued:
